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

Dataset: Open Web Text

Neuron 1682 in Layer 4

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: 1.9018. Min Range: -1.9018

Max Act: 1.9018. Min Act: -0.1700

Data Index: 3653063 (Open Web Text)

Max Activating Token Index: 384

Text #1

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.8393. Min Act: -0.1700

Data Index: 3211525 (Open Web Text)

Max Activating Token Index: 215

Text #2

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.8229. Min Act: -0.1700

Data Index: 3599484 (Open Web Text)

Max Activating Token Index: 283

Text #3

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.8114. Min Act: -0.1700

Data Index: 3966721 (Open Web Text)

Max Activating Token Index: 314

Text #4

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7811. Min Act: -0.1700

Data Index: 8232942 (Open Web Text)

Max Activating Token Index: 373

Text #5

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7709. Min Act: -0.1700

Data Index: 6722024 (Open Web Text)

Max Activating Token Index: 247

Text #6

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7749. Min Act: -0.1700

Data Index: 99258 (Open Web Text)

Max Activating Token Index: 292

Text #7

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7519. Min Act: -0.1700

Data Index: 4897583 (Open Web Text)

Max Activating Token Index: 952

Text #8

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7508. Min Act: -0.1700

Data Index: 1587341 (Open Web Text)

Max Activating Token Index: 563

Text #9

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7658. Min Act: -0.1700

Data Index: 4016672 (Open Web Text)

Max Activating Token Index: 492

Text #10

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7464. Min Act: -0.1700

Data Index: 8154895 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7491. Min Act: -0.1700

Data Index: 4814225 (Open Web Text)

Max Activating Token Index: 576

Text #12

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7396. Min Act: -0.1700

Data Index: 3210808 (Open Web Text)

Max Activating Token Index: 29

Text #13

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7621. Min Act: -0.1700

Data Index: 5209339 (Open Web Text)

Max Activating Token Index: 429

Text #14

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7379. Min Act: -0.1700

Data Index: 2941392 (Open Web Text)

Max Activating Token Index: 596

Text #15

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7353. Min Act: -0.1700

Data Index: 8674741 (Open Web Text)

Max Activating Token Index: 559

Text #16

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7405. Min Act: -0.1700

Data Index: 7879523 (Open Web Text)

Max Activating Token Index: 705

Text #17

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7123. Min Act: -0.1700

Data Index: 4832133 (Open Web Text)

Max Activating Token Index: 467

Text #18

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7274. Min Act: -0.1700

Data Index: 4832149 (Open Web Text)

Max Activating Token Index: 546

Text #19

Max Range: 1.9018. Min Range: -1.9018

Max Act: 1.7394. Min Act: -0.1700

Data Index: 1386235 (Open Web Text)

Max Activating Token Index: 109