Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1055 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3393. Min Range: -5.3393

Max Act: 5.3080. Min Act: -0.1700

Data Index: 576418 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 5.3393. Min Range: -5.3393

Max Act: 5.3393. Min Act: -0.1700

Data Index: 600668 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 5.3393. Min Range: -5.3393

Max Act: 5.1205. Min Act: -0.1700

Data Index: 755285 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 5.3393. Min Range: -5.3393

Max Act: 5.0580. Min Act: -0.1700

Data Index: 10438 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 5.3393. Min Range: -5.3393

Max Act: 5.0580. Min Act: -0.1700

Data Index: 610482 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 5.3393. Min Range: -5.3393

Max Act: 5.0268. Min Act: -0.1700

Data Index: 1285816 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9955. Min Act: -0.1700

Data Index: 1248577 (C4 (Web Text))

Max Activating Token Index: 949

Text #7

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9955. Min Act: -0.1700

Data Index: 416239 (C4 (Web Text))

Max Activating Token Index: 760

Text #8

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9955. Min Act: -0.1700

Data Index: 510819 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9643. Min Act: -0.1700

Data Index: 477343 (C4 (Web Text))

Max Activating Token Index: 783

Text #10

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9330. Min Act: -0.1700

Data Index: 175767 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9018. Min Act: -0.1700

Data Index: 1165401 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9330. Min Act: -0.1700

Data Index: 476938 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9330. Min Act: -0.1700

Data Index: 244777 (C4 (Web Text))

Max Activating Token Index: 416

Text #14

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9330. Min Act: -0.1700

Data Index: 881868 (C4 (Web Text))

Max Activating Token Index: 73

Text #15

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9018. Min Act: -0.1700

Data Index: 339415 (C4 (Web Text))

Max Activating Token Index: 291

Text #16

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9018. Min Act: -0.1700

Data Index: 496440 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9955. Min Act: -0.1700

Data Index: 1158237 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9330. Min Act: -0.1700

Data Index: 523571 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 5.3393. Min Range: -5.3393

Max Act: 4.9018. Min Act: -0.1700

Data Index: 1105392 (C4 (Web Text))

Max Activating Token Index: 82