Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3149 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.3033. Min Act: -0.0000

Data Index: 195493 (C4 (Web Text))

Max Activating Token Index: 103

Text #1

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7393. Min Act: -0.0000

Data Index: 1034088 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.3738. Min Act: -0.0000

Data Index: 405016 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5171. Min Act: -0.0000

Data Index: 1082425 (C4 (Web Text))

Max Activating Token Index: 373

Text #4

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5001. Min Act: -0.0000

Data Index: 231248 (C4 (Web Text))

Max Activating Token Index: 92

Text #5

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6609. Min Act: -0.0000

Data Index: 721472 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.2952. Min Act: -0.0000

Data Index: 1069908 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4257. Min Act: -0.0000

Data Index: 778390 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4159. Min Act: -0.0000

Data Index: 172110 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5915. Min Act: -0.0000

Data Index: 818511 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4065. Min Act: -0.0000

Data Index: 1147266 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4238. Min Act: -0.0000

Data Index: 758241 (C4 (Web Text))

Max Activating Token Index: 500

Text #12

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4140. Min Act: -0.0000

Data Index: 168123 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5623. Min Act: -0.0000

Data Index: 1024812 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.3575. Min Act: -0.0000

Data Index: 643000 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.3501. Min Act: -0.0000

Data Index: 1010318 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.2080. Min Act: -0.0000

Data Index: 883418 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4506. Min Act: -0.0000

Data Index: 196549 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4423. Min Act: -0.0000

Data Index: 866978 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.4087. Min Act: -0.0000

Data Index: 1220863 (C4 (Web Text))

Max Activating Token Index: 365