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

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

Neuron 854 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.6234. Min Act: -0.0000

Data Index: 915799 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4606. Min Act: -0.0000

Data Index: 327449 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.4479. Min Act: -0.0000

Data Index: 457868 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.2081. Min Act: -0.0000

Data Index: 180555 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 3.6234. Min Range: -3.6234

Max Act: 3.0067. Min Act: -0.0000

Data Index: 1261183 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.9825. Min Act: -0.0000

Data Index: 352879 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.8327. Min Act: -0.0000

Data Index: 1236454 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.7801. Min Act: -0.0000

Data Index: 490573 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.8860. Min Act: -0.0000

Data Index: 344555 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.7289. Min Act: -0.0000

Data Index: 21023 (C4 (Web Text))

Max Activating Token Index: 268

Text #10

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.7228. Min Act: -0.0000

Data Index: 1200482 (C4 (Web Text))

Max Activating Token Index: 935

Text #11

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.7024. Min Act: -0.0000

Data Index: 802060 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.6823. Min Act: -0.0000

Data Index: 461506 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.6620. Min Act: -0.0000

Data Index: 246122 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.7497. Min Act: -0.0000

Data Index: 769015 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.6269. Min Act: -0.0000

Data Index: 1056042 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.5880. Min Act: -0.0000

Data Index: 419429 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.5890. Min Act: -0.0000

Data Index: 855603 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.7196. Min Act: -0.0000

Data Index: 650716 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 3.6234. Min Range: -3.6234

Max Act: 2.4455. Min Act: -0.0000

Data Index: 1074916 (C4 (Web Text))

Max Activating Token Index: 459