< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 332 in Layer 1

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: 2.0085. Min Range: -2.0085

Max Act: 2.0085. Min Act: -0.1700

Data Index: 2829071 (Open Web Text)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9834. Min Act: -0.1699

Data Index: 5797344 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9814. Min Act: -0.1700

Data Index: 6064818 (Open Web Text)

Max Activating Token Index: 152

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9859. Min Act: -0.1700

Data Index: 8124694 (Open Web Text)

Max Activating Token Index: 200

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9776. Min Act: -0.1700

Data Index: 8124693 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9513. Min Act: -0.1700

Data Index: 607475 (Open Web Text)

Max Activating Token Index: 62

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9360. Min Act: -0.1700

Data Index: 6217225 (Open Web Text)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9025. Min Act: -0.1700

Data Index: 560488 (Open Web Text)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9128. Min Act: -0.1700

Data Index: 2448946 (Open Web Text)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8943. Min Act: -0.1700

Data Index: 4321793 (Open Web Text)

Max Activating Token Index: 113

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.9012. Min Act: -0.1700

Data Index: 8624051 (Open Web Text)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8932. Min Act: -0.1700

Data Index: 4160387 (Open Web Text)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8936. Min Act: -0.1700

Data Index: 1159248 (Open Web Text)

Max Activating Token Index: 266

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8882. Min Act: -0.1700

Data Index: 980873 (Open Web Text)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8891. Min Act: -0.1700

Data Index: 3760001 (Open Web Text)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8798. Min Act: -0.1700

Data Index: 2739829 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8788. Min Act: -0.1700

Data Index: 6217218 (Open Web Text)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8816. Min Act: -0.1700

Data Index: 5123210 (Open Web Text)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8843. Min Act: -0.1700

Data Index: 3185557 (Open Web Text)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.0085. Min Range: -2.0085

Max Act: 1.8776. Min Act: -0.1700

Data Index: 8624052 (Open Web Text)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #19