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

Dataset: Open Web Text

Neuron 58 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: 3.5743. Min Range: -3.5743

Max Act: 3.5743. Min Act: -0.1700

Data Index: 7515818 (Open Web Text)

Max Activating Token Index: 398

Text #1

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.5636. Min Act: -0.1700

Data Index: 2125528 (Open Web Text)

Max Activating Token Index: 117

Text #2

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.5539. Min Act: -0.1700

Data Index: 1751001 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4939. Min Act: -0.1700

Data Index: 4646976 (Open Web Text)

Max Activating Token Index: 700

Text #4

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4742. Min Act: -0.1700

Data Index: 88243 (Open Web Text)

Max Activating Token Index: 212

Text #5

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4496. Min Act: -0.1700

Data Index: 7503936 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.5031. Min Act: -0.1700

Data Index: 6803286 (Open Web Text)

Max Activating Token Index: 429

Text #7

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.5115. Min Act: -0.1700

Data Index: 8816665 (Open Web Text)

Max Activating Token Index: 772

Text #8

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4709. Min Act: -0.1700

Data Index: 5534508 (Open Web Text)

Max Activating Token Index: 612

Text #9

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4557. Min Act: -0.1700

Data Index: 6565937 (Open Web Text)

Max Activating Token Index: 217

Text #10

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4753. Min Act: -0.1700

Data Index: 7762594 (Open Web Text)

Max Activating Token Index: 367

Text #11

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4034. Min Act: -0.1700

Data Index: 8527528 (Open Web Text)

Max Activating Token Index: 618

Text #12

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4650. Min Act: -0.1700

Data Index: 807669 (Open Web Text)

Max Activating Token Index: 923

Text #13

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4358. Min Act: -0.1700

Data Index: 2342804 (Open Web Text)

Max Activating Token Index: 368

Text #14

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4338. Min Act: -0.1700

Data Index: 6488671 (Open Web Text)

Max Activating Token Index: 68

Text #15

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4274. Min Act: -0.1700

Data Index: 7017696 (Open Web Text)

Max Activating Token Index: 727

Text #16

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4176. Min Act: -0.1700

Data Index: 6950716 (Open Web Text)

Max Activating Token Index: 437

Text #17

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4296. Min Act: -0.1700

Data Index: 433812 (Open Web Text)

Max Activating Token Index: 475

Text #18

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4171. Min Act: -0.1700

Data Index: 2380916 (Open Web Text)

Max Activating Token Index: 19

Text #19

Max Range: 3.5743. Min Range: -3.5743

Max Act: 3.4234. Min Act: -0.1700

Data Index: 6993067 (Open Web Text)

Max Activating Token Index: 32