< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1796 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.4347. Min Act: -0.1700

Data Index: 5539390 (Open Web Text)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.4376. Min Act: -0.1700

Data Index: 1379404 (Open Web Text)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.4308. Min Act: -0.1700

Data Index: 7002884 (Open Web Text)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.4161. Min Act: -0.1700

Data Index: 1989323 (Open Web Text)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.4173. Min Act: -0.1700

Data Index: 4514117 (Open Web Text)

Max Activating Token Index: 238

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.4097. Min Act: -0.1700

Data Index: 807264 (Open Web Text)

Max Activating Token Index: 112

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3962. Min Act: -0.1700

Data Index: 7617450 (Open Web Text)

Max Activating Token Index: 264

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3794. Min Act: -0.1700

Data Index: 8170957 (Open Web Text)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3824. Min Act: -0.1700

Data Index: 655121 (Open Web Text)

Max Activating Token Index: 564

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3759. Min Act: -0.1700

Data Index: 50332 (Open Web Text)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3882. Min Act: -0.1700

Data Index: 5791023 (Open Web Text)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3781. Min Act: -0.1700

Data Index: 1331152 (Open Web Text)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3520. Min Act: -0.1700

Data Index: 3359186 (Open Web Text)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3463. Min Act: -0.1700

Data Index: 3664570 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3577. Min Act: -0.1700

Data Index: 6247010 (Open Web Text)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3413. Min Act: -0.1700

Data Index: 3403041 (Open Web Text)

Max Activating Token Index: 644

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3416. Min Act: -0.1700

Data Index: 743642 (Open Web Text)

Max Activating Token Index: 597

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3168. Min Act: -0.1700

Data Index: 7557126 (Open Web Text)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3359. Min Act: -0.1700

Data Index: 4904623 (Open Web Text)

Max Activating Token Index: 714

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.4376. Min Range: -2.4376

Max Act: 2.3207. Min Act: -0.1700

Data Index: 5168064 (Open Web Text)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #19