Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3965 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4376. Min Act: -0.0000

Data Index: 130834 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.4178. Min Act: -0.0000

Data Index: 1246203 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3344. Min Act: -0.0001

Data Index: 859926 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3461. Min Act: -0.0000

Data Index: 137749 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3560. Min Act: -0.0000

Data Index: 591886 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3393. Min Act: -0.0001

Data Index: 510009 (C4 (Web Text))

Max Activating Token Index: 990

Text #6

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3449. Min Act: -0.0001

Data Index: 499612 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3306. Min Act: -0.0000

Data Index: 724998 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3277. Min Act: -0.0000

Data Index: 104705 (C4 (Web Text))

Max Activating Token Index: 217

Text #9

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3036. Min Act: -0.0000

Data Index: 673263 (C4 (Web Text))

Max Activating Token Index: 332

Text #10

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3151. Min Act: -0.0001

Data Index: 948461 (C4 (Web Text))

Max Activating Token Index: 176

Text #11

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3242. Min Act: -0.0001

Data Index: 790952 (C4 (Web Text))

Max Activating Token Index: 936

Text #12

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2938. Min Act: -0.0001

Data Index: 1039138 (C4 (Web Text))

Max Activating Token Index: 378

Text #13

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3083. Min Act: -0.0000

Data Index: 988621 (C4 (Web Text))

Max Activating Token Index: 688

Text #14

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3000. Min Act: -0.0000

Data Index: 290515 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2862. Min Act: -0.0000

Data Index: 171559 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3022. Min Act: -0.0000

Data Index: 525655 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.3150. Min Act: -0.0000

Data Index: 550912 (C4 (Web Text))

Max Activating Token Index: 405

Text #18

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2930. Min Act: -0.0001

Data Index: 355288 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.4376. Min Range: -0.4376

Max Act: 0.2892. Min Act: -0.0000

Data Index: 729005 (C4 (Web Text))

Max Activating Token Index: 214