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

Dataset: Open Web Text

Neuron 1543 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: 4.1545. Min Range: -4.1545

Max Act: 4.1545. Min Act: -0.1700

Data Index: 8629054 (Open Web Text)

Max Activating Token Index: 124

Text #1

Max Range: 4.1545. Min Range: -4.1545

Max Act: 4.0264. Min Act: -0.1700

Data Index: 2637803 (Open Web Text)

Max Activating Token Index: 212

Text #2

Max Range: 4.1545. Min Range: -4.1545

Max Act: 4.0214. Min Act: -0.1700

Data Index: 2596763 (Open Web Text)

Max Activating Token Index: 625

Text #3

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.9688. Min Act: -0.1700

Data Index: 3076615 (Open Web Text)

Max Activating Token Index: 787

Text #4

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.9503. Min Act: -0.1700

Data Index: 439394 (Open Web Text)

Max Activating Token Index: 731

Text #5

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.9239. Min Act: -0.1700

Data Index: 3129172 (Open Web Text)

Max Activating Token Index: 268

Text #6

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.9364. Min Act: -0.1700

Data Index: 2478492 (Open Web Text)

Max Activating Token Index: 353

Text #7

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.9280. Min Act: -0.1700

Data Index: 4513157 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8944. Min Act: -0.1700

Data Index: 3020939 (Open Web Text)

Max Activating Token Index: 883

Text #9

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.9248. Min Act: -0.1700

Data Index: 52531 (Open Web Text)

Max Activating Token Index: 1004

Text #10

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8790. Min Act: -0.1700

Data Index: 751370 (Open Web Text)

Max Activating Token Index: 326

Text #11

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.9200. Min Act: -0.1700

Data Index: 5716072 (Open Web Text)

Max Activating Token Index: 108

Text #12

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8793. Min Act: -0.1700

Data Index: 7296665 (Open Web Text)

Max Activating Token Index: 26

Text #13

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8621. Min Act: -0.1700

Data Index: 2213331 (Open Web Text)

Max Activating Token Index: 717

Text #14

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8600. Min Act: -0.1700

Data Index: 6992957 (Open Web Text)

Max Activating Token Index: 170

Text #15

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8316. Min Act: -0.1700

Data Index: 1875110 (Open Web Text)

Max Activating Token Index: 275

Text #16

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8268. Min Act: -0.1700

Data Index: 3209547 (Open Web Text)

Max Activating Token Index: 536

Text #17

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8174. Min Act: -0.1700

Data Index: 3432578 (Open Web Text)

Max Activating Token Index: 94

Text #18

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.7842. Min Act: -0.1700

Data Index: 6487268 (Open Web Text)

Max Activating Token Index: 48

Text #19

Max Range: 4.1545. Min Range: -4.1545

Max Act: 3.8075. Min Act: -0.1700

Data Index: 5104030 (Open Web Text)

Max Activating Token Index: 405