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

Dataset: Open Web Text

Neuron 578 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: 1.5172. Min Range: -1.5172

Max Act: 1.5172. Min Act: -0.1700

Data Index: 2023766 (Open Web Text)

Max Activating Token Index: 403

Text #1

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4439. Min Act: -0.1700

Data Index: 4004683 (Open Web Text)

Max Activating Token Index: 69

Text #2

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4271. Min Act: -0.1700

Data Index: 8551026 (Open Web Text)

Max Activating Token Index: 582

Text #3

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4351. Min Act: -0.1700

Data Index: 1781114 (Open Web Text)

Max Activating Token Index: 344

Text #4

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4240. Min Act: -0.1700

Data Index: 4492494 (Open Web Text)

Max Activating Token Index: 991

Text #5

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4265. Min Act: -0.1700

Data Index: 479882 (Open Web Text)

Max Activating Token Index: 337

Text #6

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4226. Min Act: -0.1700

Data Index: 2656018 (Open Web Text)

Max Activating Token Index: 572

Text #7

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4202. Min Act: -0.1700

Data Index: 7640836 (Open Web Text)

Max Activating Token Index: 1005

Text #8

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4107. Min Act: -0.1700

Data Index: 7515335 (Open Web Text)

Max Activating Token Index: 355

Text #9

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4167. Min Act: -0.1700

Data Index: 8167771 (Open Web Text)

Max Activating Token Index: 547

Text #10

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4145. Min Act: -0.1700

Data Index: 6999461 (Open Web Text)

Max Activating Token Index: 622

Text #11

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4056. Min Act: -0.1700

Data Index: 925447 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4113. Min Act: -0.1700

Data Index: 6706871 (Open Web Text)

Max Activating Token Index: 84

Text #13

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4076. Min Act: -0.1700

Data Index: 4700220 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.3984. Min Act: -0.1700

Data Index: 1669485 (Open Web Text)

Max Activating Token Index: 339

Text #15

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4035. Min Act: -0.1700

Data Index: 2195758 (Open Web Text)

Max Activating Token Index: 477

Text #16

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4059. Min Act: -0.1700

Data Index: 6437689 (Open Web Text)

Max Activating Token Index: 687

Text #17

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4068. Min Act: -0.1700

Data Index: 1174295 (Open Web Text)

Max Activating Token Index: 153

Text #18

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4045. Min Act: -0.1700

Data Index: 2389720 (Open Web Text)

Max Activating Token Index: 81

Text #19

Max Range: 1.5172. Min Range: -1.5172

Max Act: 1.4015. Min Act: -0.1700

Data Index: 5112283 (Open Web Text)

Max Activating Token Index: 939