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

Dataset: Open Web Text

Neuron 50 in Layer 2

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: 4.6048. Min Range: -4.6048

Max Act: 4.6048. Min Act: -0.1700

Data Index: 6548050 (Open Web Text)

Max Activating Token Index: 419

Text #1

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4955. Min Act: -0.1700

Data Index: 7183205 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.5342. Min Act: -0.1700

Data Index: 8431774 (Open Web Text)

Max Activating Token Index: 680

Text #3

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.5534. Min Act: -0.1700

Data Index: 7965641 (Open Web Text)

Max Activating Token Index: 429

Text #4

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4646. Min Act: -0.1700

Data Index: 5463001 (Open Web Text)

Max Activating Token Index: 57

Text #5

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4722. Min Act: -0.1700

Data Index: 6215590 (Open Web Text)

Max Activating Token Index: 853

Text #6

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4997. Min Act: -0.1700

Data Index: 6903251 (Open Web Text)

Max Activating Token Index: 558

Text #7

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4933. Min Act: -0.1700

Data Index: 3068192 (Open Web Text)

Max Activating Token Index: 261

Text #8

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4170. Min Act: -0.1700

Data Index: 8507649 (Open Web Text)

Max Activating Token Index: 621

Text #9

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4402. Min Act: -0.1700

Data Index: 1038067 (Open Web Text)

Max Activating Token Index: 234

Text #10

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4452. Min Act: -0.1700

Data Index: 3184520 (Open Web Text)

Max Activating Token Index: 429

Text #11

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4602. Min Act: -0.1700

Data Index: 6517974 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4785. Min Act: -0.1700

Data Index: 8471798 (Open Web Text)

Max Activating Token Index: 379

Text #13

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4824. Min Act: -0.1700

Data Index: 3744147 (Open Web Text)

Max Activating Token Index: 435

Text #14

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4464. Min Act: -0.1700

Data Index: 3384402 (Open Web Text)

Max Activating Token Index: 132

Text #15

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4115. Min Act: -0.1700

Data Index: 7610699 (Open Web Text)

Max Activating Token Index: 43

Text #16

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4403. Min Act: -0.1700

Data Index: 3667640 (Open Web Text)

Max Activating Token Index: 231

Text #17

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4135. Min Act: -0.1700

Data Index: 7540167 (Open Web Text)

Max Activating Token Index: 182

Text #18

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4308. Min Act: -0.1700

Data Index: 4277927 (Open Web Text)

Max Activating Token Index: 583

Text #19

Max Range: 4.6048. Min Range: -4.6048

Max Act: 4.4167. Min Act: -0.1700

Data Index: 2217543 (Open Web Text)

Max Activating Token Index: 245