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

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

Neuron 3595 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3950. Min Act: -0.0001

Data Index: 1526478 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3330. Min Act: -0.0001

Data Index: 1577326 (Python Code)

Max Activating Token Index: 42

Text #2

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3409. Min Act: -0.0001

Data Index: 1651464 (Python Code)

Max Activating Token Index: 462

Text #3

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1015551 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3209. Min Act: -0.0001

Data Index: 1402149 (Python Code)

Max Activating Token Index: 382

Text #5

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3442. Min Act: -0.0001

Data Index: 1603849 (Python Code)

Max Activating Token Index: 181

Text #6

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3213. Min Act: -0.0001

Data Index: 1159270 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3077. Min Act: -0.0001

Data Index: 1475913 (Python Code)

Max Activating Token Index: 316

Text #8

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3094. Min Act: -0.0000

Data Index: 414897 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2603. Min Act: -0.0000

Data Index: 907705 (C4 (Web Text))

Max Activating Token Index: 355

Text #10

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2990. Min Act: -0.0000

Data Index: 598382 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2779. Min Act: -0.0001

Data Index: 1265542 (C4 (Web Text))

Max Activating Token Index: 299

Text #12

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3283. Min Act: -0.0001

Data Index: 349001 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2848. Min Act: -0.0000

Data Index: 144093 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2909. Min Act: -0.0000

Data Index: 1071407 (C4 (Web Text))

Max Activating Token Index: 1022

Text #15

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2906. Min Act: -0.0001

Data Index: 519701 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2875. Min Act: -0.0000

Data Index: 576358 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.3093. Min Act: -0.0000

Data Index: 540936 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2567. Min Act: -0.0001

Data Index: 909443 (C4 (Web Text))

Max Activating Token Index: 668

Text #19

Max Range: 0.3950. Min Range: -0.3950

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1074729 (C4 (Web Text))

Max Activating Token Index: 702