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

Dataset: Open Web Text

Neuron 241 in Layer 5

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: 3.9893. Min Range: -3.9893

Max Act: 3.9730. Min Act: -0.1700

Data Index: 650555 (Open Web Text)

Max Activating Token Index: 257

Text #1

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9893. Min Act: -0.1700

Data Index: 1960130 (Open Web Text)

Max Activating Token Index: 79

Text #2

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9432. Min Act: -0.1700

Data Index: 1115449 (Open Web Text)

Max Activating Token Index: 87

Text #3

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9317. Min Act: -0.1700

Data Index: 1684016 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.9070. Min Act: -0.1700

Data Index: 1960131 (Open Web Text)

Max Activating Token Index: 775

Text #5

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8687. Min Act: -0.1700

Data Index: 4752503 (Open Web Text)

Max Activating Token Index: 235

Text #6

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8732. Min Act: -0.1700

Data Index: 2971276 (Open Web Text)

Max Activating Token Index: 821

Text #7

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8081. Min Act: -0.1700

Data Index: 6943469 (Open Web Text)

Max Activating Token Index: 933

Text #8

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8345. Min Act: -0.1700

Data Index: 8356595 (Open Web Text)

Max Activating Token Index: 348

Text #9

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.7862. Min Act: -0.1700

Data Index: 2578368 (Open Web Text)

Max Activating Token Index: 695

Text #10

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8601. Min Act: -0.1700

Data Index: 7807618 (Open Web Text)

Max Activating Token Index: 945

Text #11

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8448. Min Act: -0.1700

Data Index: 5585195 (Open Web Text)

Max Activating Token Index: 570

Text #12

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8519. Min Act: -0.1700

Data Index: 6457368 (Open Web Text)

Max Activating Token Index: 920

Text #13

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8246. Min Act: -0.1700

Data Index: 633193 (Open Web Text)

Max Activating Token Index: 438

Text #14

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8119. Min Act: -0.1700

Data Index: 8397121 (Open Web Text)

Max Activating Token Index: 32

Text #15

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.7549. Min Act: -0.1700

Data Index: 5687656 (Open Web Text)

Max Activating Token Index: 658

Text #16

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.7808. Min Act: -0.1700

Data Index: 3996761 (Open Web Text)

Max Activating Token Index: 85

Text #17

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.8036. Min Act: -0.1700

Data Index: 1321845 (Open Web Text)

Max Activating Token Index: 522

Text #18

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.7835. Min Act: -0.1700

Data Index: 4685273 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 3.9893. Min Range: -3.9893

Max Act: 3.7995. Min Act: -0.1700

Data Index: 1683899 (Open Web Text)

Max Activating Token Index: 455