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

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

Neuron 928 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3337. Min Act: -0.0002

Data Index: 1006219 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3440. Min Act: -0.0002

Data Index: 584340 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3688. Min Act: -0.0002

Data Index: 592344 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3107. Min Act: -0.0002

Data Index: 536301 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3440. Min Act: -0.0002

Data Index: 402475 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3258. Min Act: -0.0001

Data Index: 1564364 (Python Code)

Max Activating Token Index: 302

Text #6

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3105. Min Act: -0.0002

Data Index: 665347 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3354. Min Act: -0.0002

Data Index: 1297616 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3362. Min Act: -0.0002

Data Index: 917551 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3282. Min Act: -0.0002

Data Index: 1173398 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3283. Min Act: -0.0002

Data Index: 323641 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3164. Min Act: -0.0002

Data Index: 51468 (C4 (Web Text))

Max Activating Token Index: 728

Text #12

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3159. Min Act: -0.0002

Data Index: 1110455 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3320. Min Act: -0.0002

Data Index: 470022 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3465. Min Act: -0.0002

Data Index: 974392 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3068. Min Act: -0.0002

Data Index: 807439 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3281. Min Act: -0.0002

Data Index: 125589 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3078. Min Act: -0.0002

Data Index: 627240 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3178. Min Act: -0.0002

Data Index: 832428 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.3688. Min Range: -0.3688

Max Act: 0.3039. Min Act: -0.0002

Data Index: 1298319 (C4 (Web Text))

Max Activating Token Index: 360