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

Dataset: Open Web Text

Neuron 1206 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: 2.7235. Min Range: -2.7235

Max Act: 2.7235. Min Act: -0.1700

Data Index: 7673071 (Open Web Text)

Max Activating Token Index: 338

Text #1

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.7051. Min Act: -0.1700

Data Index: 8735203 (Open Web Text)

Max Activating Token Index: 429

Text #2

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6955. Min Act: -0.1700

Data Index: 6443405 (Open Web Text)

Max Activating Token Index: 1010

Text #3

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6397. Min Act: -0.1700

Data Index: 4415180 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6338. Min Act: -0.1700

Data Index: 2326818 (Open Web Text)

Max Activating Token Index: 227

Text #5

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6186. Min Act: -0.1700

Data Index: 7829321 (Open Web Text)

Max Activating Token Index: 467

Text #6

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6300. Min Act: -0.1700

Data Index: 1266506 (Open Web Text)

Max Activating Token Index: 448

Text #7

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6088. Min Act: -0.1700

Data Index: 4899336 (Open Web Text)

Max Activating Token Index: 116

Text #8

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6293. Min Act: -0.1700

Data Index: 5769277 (Open Web Text)

Max Activating Token Index: 466

Text #9

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6124. Min Act: -0.1700

Data Index: 140937 (Open Web Text)

Max Activating Token Index: 850

Text #10

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.6055. Min Act: -0.1700

Data Index: 1207358 (Open Web Text)

Max Activating Token Index: 328

Text #11

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5887. Min Act: -0.1700

Data Index: 3233150 (Open Web Text)

Max Activating Token Index: 815

Text #12

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5944. Min Act: -0.1700

Data Index: 3664306 (Open Web Text)

Max Activating Token Index: 40

Text #13

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5949. Min Act: -0.1700

Data Index: 16214 (Open Web Text)

Max Activating Token Index: 816

Text #14

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5748. Min Act: -0.1700

Data Index: 3732546 (Open Web Text)

Max Activating Token Index: 1019

Text #15

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5645. Min Act: -0.1700

Data Index: 6412885 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5734. Min Act: -0.1700

Data Index: 8528196 (Open Web Text)

Max Activating Token Index: 605

Text #17

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5442. Min Act: -0.1700

Data Index: 2027250 (Open Web Text)

Max Activating Token Index: 854

Text #18

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5472. Min Act: -0.1700

Data Index: 3783604 (Open Web Text)

Max Activating Token Index: 834

Text #19

Max Range: 2.7235. Min Range: -2.7235

Max Act: 2.5141. Min Act: -0.1700

Data Index: 4225926 (Open Web Text)

Max Activating Token Index: 915