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

Dataset: Open Web Text

Neuron 2200 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: 4.7074. Min Range: -4.7074

Max Act: 4.7074. Min Act: -0.1700

Data Index: 2487641 (Open Web Text)

Max Activating Token Index: 928

Text #1

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.6270. Min Act: -0.1700

Data Index: 649154 (Open Web Text)

Max Activating Token Index: 911

Text #2

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.6272. Min Act: -0.1700

Data Index: 7806120 (Open Web Text)

Max Activating Token Index: 965

Text #3

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.6171. Min Act: -0.1700

Data Index: 7462010 (Open Web Text)

Max Activating Token Index: 592

Text #4

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.5587. Min Act: -0.1700

Data Index: 7885731 (Open Web Text)

Max Activating Token Index: 283

Text #5

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.5107. Min Act: -0.1700

Data Index: 7829054 (Open Web Text)

Max Activating Token Index: 148

Text #6

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.5057. Min Act: -0.1700

Data Index: 8261770 (Open Web Text)

Max Activating Token Index: 963

Text #7

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4858. Min Act: -0.1700

Data Index: 6716165 (Open Web Text)

Max Activating Token Index: 979

Text #8

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4319. Min Act: -0.1700

Data Index: 2817172 (Open Web Text)

Max Activating Token Index: 969

Text #9

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4571. Min Act: -0.1700

Data Index: 2168355 (Open Web Text)

Max Activating Token Index: 657

Text #10

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4324. Min Act: -0.1700

Data Index: 6749832 (Open Web Text)

Max Activating Token Index: 799

Text #11

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4625. Min Act: -0.1700

Data Index: 6357531 (Open Web Text)

Max Activating Token Index: 339

Text #12

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4274. Min Act: -0.1700

Data Index: 8159241 (Open Web Text)

Max Activating Token Index: 847

Text #13

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4246. Min Act: -0.1700

Data Index: 698883 (Open Web Text)

Max Activating Token Index: 374

Text #14

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4185. Min Act: -0.1700

Data Index: 2487642 (Open Web Text)

Max Activating Token Index: 34

Text #15

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4301. Min Act: -0.1700

Data Index: 2324644 (Open Web Text)

Max Activating Token Index: 885

Text #16

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4331. Min Act: -0.1700

Data Index: 4298819 (Open Web Text)

Max Activating Token Index: 679

Text #17

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4118. Min Act: -0.1700

Data Index: 1039937 (Open Web Text)

Max Activating Token Index: 353

Text #18

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4271. Min Act: -0.1700

Data Index: 1238846 (Open Web Text)

Max Activating Token Index: 498

Text #19

Max Range: 4.7074. Min Range: -4.7074

Max Act: 4.4160. Min Act: -0.1700

Data Index: 814752 (Open Web Text)

Max Activating Token Index: 879