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

Dataset: Open Web Text

Neuron 637 in Layer 3

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: 3.9815. Min Range: -3.9815

Max Act: 3.9815. Min Act: -0.1700

Data Index: 3397618 (Open Web Text)

Max Activating Token Index: 590

Text #1

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.9632. Min Act: -0.1700

Data Index: 6097669 (Open Web Text)

Max Activating Token Index: 539

Text #2

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.8824. Min Act: -0.1700

Data Index: 4957865 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.7817. Min Act: -0.1700

Data Index: 8228661 (Open Web Text)

Max Activating Token Index: 380

Text #4

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.8044. Min Act: -0.1700

Data Index: 2503321 (Open Web Text)

Max Activating Token Index: 143

Text #5

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.7244. Min Act: -0.1700

Data Index: 4681134 (Open Web Text)

Max Activating Token Index: 102

Text #6

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.7055. Min Act: -0.1700

Data Index: 4887418 (Open Web Text)

Max Activating Token Index: 18

Text #7

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.7112. Min Act: -0.1700

Data Index: 78764 (Open Web Text)

Max Activating Token Index: 290

Text #8

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.7129. Min Act: -0.1700

Data Index: 5141631 (Open Web Text)

Max Activating Token Index: 477

Text #9

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6548. Min Act: -0.1700

Data Index: 3615958 (Open Web Text)

Max Activating Token Index: 419

Text #10

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6501. Min Act: -0.1700

Data Index: 1495183 (Open Web Text)

Max Activating Token Index: 61

Text #11

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6377. Min Act: -0.1700

Data Index: 7510746 (Open Web Text)

Max Activating Token Index: 38

Text #12

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6494. Min Act: -0.1700

Data Index: 8695074 (Open Web Text)

Max Activating Token Index: 613

Text #13

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6322. Min Act: -0.1700

Data Index: 2150451 (Open Web Text)

Max Activating Token Index: 795

Text #14

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.5963. Min Act: -0.1700

Data Index: 4143834 (Open Web Text)

Max Activating Token Index: 379

Text #15

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6440. Min Act: -0.1700

Data Index: 5923630 (Open Web Text)

Max Activating Token Index: 890

Text #16

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6262. Min Act: -0.1700

Data Index: 6282855 (Open Web Text)

Max Activating Token Index: 402

Text #17

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6490. Min Act: -0.1700

Data Index: 1026477 (Open Web Text)

Max Activating Token Index: 944

Text #18

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6041. Min Act: -0.1700

Data Index: 5543674 (Open Web Text)

Max Activating Token Index: 691

Text #19

Max Range: 3.9815. Min Range: -3.9815

Max Act: 3.6549. Min Act: -0.1700

Data Index: 1026472 (Open Web Text)

Max Activating Token Index: 296