Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3394 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8792. Min Act: -0.0000

Data Index: 127565 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7989. Min Act: -0.0000

Data Index: 1260501 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6135. Min Act: -0.0000

Data Index: 717737 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.6323. Min Act: -0.0000

Data Index: 1347665 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5775. Min Act: -0.0000

Data Index: 1336146 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5718. Min Act: -0.0000

Data Index: 119371 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5304. Min Act: -0.0000

Data Index: 131508 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1139148 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5402. Min Act: -0.0000

Data Index: 563123 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5628. Min Act: -0.0000

Data Index: 1314593 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4902. Min Act: -0.0000

Data Index: 210431 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1056422 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4989. Min Act: -0.0000

Data Index: 158776 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.5418. Min Act: -0.0000

Data Index: 863712 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4796. Min Act: -0.0000

Data Index: 453120 (C4 (Web Text))

Max Activating Token Index: 401

Text #15

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4390. Min Act: -0.0000

Data Index: 1235760 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4532. Min Act: -0.0000

Data Index: 498326 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4297. Min Act: -0.0000

Data Index: 242155 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4362. Min Act: -0.0000

Data Index: 300325 (C4 (Web Text))

Max Activating Token Index: 678

Text #19

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1126571 (C4 (Web Text))

Max Activating Token Index: 653