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

Dataset: Open Web Text

Neuron 1965 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: 3.3221. Min Range: -3.3221

Max Act: 3.3221. Min Act: -0.1700

Data Index: 6129544 (Open Web Text)

Max Activating Token Index: 242

Text #1

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2434. Min Act: -0.1700

Data Index: 973921 (Open Web Text)

Max Activating Token Index: 799

Text #2

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.2102. Min Act: -0.1700

Data Index: 262971 (Open Web Text)

Max Activating Token Index: 863

Text #3

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1841. Min Act: -0.1700

Data Index: 6641796 (Open Web Text)

Max Activating Token Index: 765

Text #4

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1963. Min Act: -0.1700

Data Index: 8514361 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.1026. Min Act: -0.1700

Data Index: 5102475 (Open Web Text)

Max Activating Token Index: 164

Text #6

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0423. Min Act: -0.1700

Data Index: 92635 (Open Web Text)

Max Activating Token Index: 603

Text #7

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0329. Min Act: -0.1700

Data Index: 3900483 (Open Web Text)

Max Activating Token Index: 264

Text #8

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0453. Min Act: -0.1700

Data Index: 1801971 (Open Web Text)

Max Activating Token Index: 729

Text #9

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0699. Min Act: -0.1700

Data Index: 7750015 (Open Web Text)

Max Activating Token Index: 666

Text #10

Max Range: 3.3221. Min Range: -3.3221

Max Act: 3.0142. Min Act: -0.1700

Data Index: 3018819 (Open Web Text)

Max Activating Token Index: 195

Text #11

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9916. Min Act: -0.1700

Data Index: 4169899 (Open Web Text)

Max Activating Token Index: 847

Text #12

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9678. Min Act: -0.1700

Data Index: 1008904 (Open Web Text)

Max Activating Token Index: 238

Text #13

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9474. Min Act: -0.1700

Data Index: 3407338 (Open Web Text)

Max Activating Token Index: 642

Text #14

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9855. Min Act: -0.1700

Data Index: 6721572 (Open Web Text)

Max Activating Token Index: 415

Text #15

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9333. Min Act: -0.1700

Data Index: 5922961 (Open Web Text)

Max Activating Token Index: 349

Text #16

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9499. Min Act: -0.1700

Data Index: 2525185 (Open Web Text)

Max Activating Token Index: 650

Text #17

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9265. Min Act: -0.1700

Data Index: 1740433 (Open Web Text)

Max Activating Token Index: 328

Text #18

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9348. Min Act: -0.1700

Data Index: 2741614 (Open Web Text)

Max Activating Token Index: 103

Text #19

Max Range: 3.3221. Min Range: -3.3221

Max Act: 2.9225. Min Act: -0.1700

Data Index: 5996390 (Open Web Text)

Max Activating Token Index: 618