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

Dataset: Open Web Text

Neuron 713 in Layer 6

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: 5.3138. Min Range: -5.3138

Max Act: 5.3138. Min Act: -0.1700

Data Index: 1142201 (Open Web Text)

Max Activating Token Index: 135

Text #1

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.1984. Min Act: -0.1700

Data Index: 4745105 (Open Web Text)

Max Activating Token Index: 655

Text #2

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.2267. Min Act: -0.1700

Data Index: 3494948 (Open Web Text)

Max Activating Token Index: 438

Text #3

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.1625. Min Act: -0.1700

Data Index: 3227927 (Open Web Text)

Max Activating Token Index: 87

Text #4

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0943. Min Act: -0.1700

Data Index: 4969601 (Open Web Text)

Max Activating Token Index: 435

Text #5

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.1468. Min Act: -0.1700

Data Index: 5414398 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.1017. Min Act: -0.1700

Data Index: 2142146 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0937. Min Act: -0.1700

Data Index: 6504506 (Open Web Text)

Max Activating Token Index: 775

Text #8

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0568. Min Act: -0.1700

Data Index: 7418355 (Open Web Text)

Max Activating Token Index: 530

Text #9

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0154. Min Act: -0.1700

Data Index: 8173089 (Open Web Text)

Max Activating Token Index: 760

Text #10

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0825. Min Act: -0.1700

Data Index: 1491162 (Open Web Text)

Max Activating Token Index: 283

Text #11

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0148. Min Act: -0.1700

Data Index: 131022 (Open Web Text)

Max Activating Token Index: 329

Text #12

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0366. Min Act: -0.1700

Data Index: 5909288 (Open Web Text)

Max Activating Token Index: 130

Text #13

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0361. Min Act: -0.1700

Data Index: 1787286 (Open Web Text)

Max Activating Token Index: 235

Text #14

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0279. Min Act: -0.1700

Data Index: 464760 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0032. Min Act: -0.1700

Data Index: 2404256 (Open Web Text)

Max Activating Token Index: 700

Text #16

Max Range: 5.3138. Min Range: -5.3138

Max Act: 4.9896. Min Act: -0.1700

Data Index: 6186396 (Open Web Text)

Max Activating Token Index: 789

Text #17

Max Range: 5.3138. Min Range: -5.3138

Max Act: 5.0108. Min Act: -0.1700

Data Index: 6056882 (Open Web Text)

Max Activating Token Index: 788

Text #18

Max Range: 5.3138. Min Range: -5.3138

Max Act: 4.9706. Min Act: -0.1700

Data Index: 170648 (Open Web Text)

Max Activating Token Index: 900

Text #19

Max Range: 5.3138. Min Range: -5.3138

Max Act: 4.9745. Min Act: -0.1700

Data Index: 3729651 (Open Web Text)

Max Activating Token Index: 251