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

Dataset: Open Web Text

Neuron 1422 in Layer 1

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: 1.7142. Min Range: -1.7142

Max Act: 1.7053. Min Act: -0.1700

Data Index: 220002 (Open Web Text)

Max Activating Token Index: 546

Text #1

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.7030. Min Act: -0.1700

Data Index: 8754236 (Open Web Text)

Max Activating Token Index: 451

Text #2

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.7035. Min Act: -0.1699

Data Index: 2207170 (Open Web Text)

Max Activating Token Index: 254

Text #3

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.7142. Min Act: -0.1700

Data Index: 7483906 (Open Web Text)

Max Activating Token Index: 195

Text #4

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6889. Min Act: -0.1700

Data Index: 5711998 (Open Web Text)

Max Activating Token Index: 169

Text #5

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6833. Min Act: -0.1700

Data Index: 8212709 (Open Web Text)

Max Activating Token Index: 814

Text #6

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6702. Min Act: -0.1700

Data Index: 1372504 (Open Web Text)

Max Activating Token Index: 535

Text #7

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6574. Min Act: -0.1700

Data Index: 8796984 (Open Web Text)

Max Activating Token Index: 332

Text #8

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6626. Min Act: -0.1700

Data Index: 6473650 (Open Web Text)

Max Activating Token Index: 76

Text #9

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6679. Min Act: -0.1700

Data Index: 4138316 (Open Web Text)

Max Activating Token Index: 626

Text #10

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6636. Min Act: -0.1700

Data Index: 4776625 (Open Web Text)

Max Activating Token Index: 695

Text #11

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6532. Min Act: -0.1700

Data Index: 5637539 (Open Web Text)

Max Activating Token Index: 1020

Text #12

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6557. Min Act: -0.1700

Data Index: 437236 (Open Web Text)

Max Activating Token Index: 271

Text #13

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6500. Min Act: -0.1700

Data Index: 5931542 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6491. Min Act: -0.1700

Data Index: 7331581 (Open Web Text)

Max Activating Token Index: 524

Text #15

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6438. Min Act: -0.1700

Data Index: 1699939 (Open Web Text)

Max Activating Token Index: 900

Text #16

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6472. Min Act: -0.1700

Data Index: 2535128 (Open Web Text)

Max Activating Token Index: 459

Text #17

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6415. Min Act: -0.1700

Data Index: 6325735 (Open Web Text)

Max Activating Token Index: 190

Text #18

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6375. Min Act: -0.1700

Data Index: 4286885 (Open Web Text)

Max Activating Token Index: 195

Text #19

Max Range: 1.7142. Min Range: -1.7142

Max Act: 1.6442. Min Act: -0.1700

Data Index: 7146450 (Open Web Text)

Max Activating Token Index: 292