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

Dataset: Open Web Text

Neuron 156 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: 3.8135. Min Range: -3.8135

Max Act: 3.8135. Min Act: -0.1700

Data Index: 487597 (Open Web Text)

Max Activating Token Index: 16

Text #1

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.7366. Min Act: -0.1700

Data Index: 5833438 (Open Web Text)

Max Activating Token Index: 655

Text #2

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.7144. Min Act: -0.1700

Data Index: 1381442 (Open Web Text)

Max Activating Token Index: 490

Text #3

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.7253. Min Act: -0.1700

Data Index: 1876207 (Open Web Text)

Max Activating Token Index: 494

Text #4

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.7114. Min Act: -0.1700

Data Index: 6828807 (Open Web Text)

Max Activating Token Index: 477

Text #5

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6745. Min Act: -0.1700

Data Index: 8548072 (Open Web Text)

Max Activating Token Index: 193

Text #6

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6781. Min Act: -0.1700

Data Index: 2411013 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6707. Min Act: -0.1700

Data Index: 5377620 (Open Web Text)

Max Activating Token Index: 123

Text #8

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6543. Min Act: -0.1700

Data Index: 307900 (Open Web Text)

Max Activating Token Index: 576

Text #9

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6476. Min Act: -0.1700

Data Index: 6634625 (Open Web Text)

Max Activating Token Index: 49

Text #10

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6429. Min Act: -0.1700

Data Index: 2838520 (Open Web Text)

Max Activating Token Index: 469

Text #11

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6258. Min Act: -0.1700

Data Index: 4967660 (Open Web Text)

Max Activating Token Index: 558

Text #12

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6324. Min Act: -0.1700

Data Index: 1282564 (Open Web Text)

Max Activating Token Index: 1019

Text #13

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6402. Min Act: -0.1700

Data Index: 5101064 (Open Web Text)

Max Activating Token Index: 496

Text #14

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6274. Min Act: -0.1700

Data Index: 2552323 (Open Web Text)

Max Activating Token Index: 408

Text #15

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6347. Min Act: -0.1700

Data Index: 2394811 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6385. Min Act: -0.1700

Data Index: 1978099 (Open Web Text)

Max Activating Token Index: 584

Text #17

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6213. Min Act: -0.1700

Data Index: 7027194 (Open Web Text)

Max Activating Token Index: 148

Text #18

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6104. Min Act: -0.1700

Data Index: 8446179 (Open Web Text)

Max Activating Token Index: 116

Text #19

Max Range: 3.8135. Min Range: -3.8135

Max Act: 3.6221. Min Act: -0.1700

Data Index: 23343 (Open Web Text)

Max Activating Token Index: 408