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

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

Neuron 4456 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5696. Min Range: -5.5696

Max Act: 5.5696. Min Act: -0.0000

Data Index: 376369 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 5.5696. Min Range: -5.5696

Max Act: 4.5205. Min Act: -0.0000

Data Index: 515836 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 5.5696. Min Range: -5.5696

Max Act: 4.0301. Min Act: -0.0000

Data Index: 891980 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 5.5696. Min Range: -5.5696

Max Act: 4.0661. Min Act: -0.0000

Data Index: 1218301 (C4 (Web Text))

Max Activating Token Index: 96

Text #4

Max Range: 5.5696. Min Range: -5.5696

Max Act: 4.1771. Min Act: -0.0000

Data Index: 1027876 (C4 (Web Text))

Max Activating Token Index: 354

Text #5

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.9415. Min Act: -0.0000

Data Index: 695567 (C4 (Web Text))

Max Activating Token Index: 971

Text #6

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.9040. Min Act: -0.0000

Data Index: 1164166 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.5693. Min Act: -0.0000

Data Index: 566400 (C4 (Web Text))

Max Activating Token Index: 711

Text #8

Max Range: 5.5696. Min Range: -5.5696

Max Act: 4.0399. Min Act: -0.0000

Data Index: 1066861 (C4 (Web Text))

Max Activating Token Index: 876

Text #9

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.6367. Min Act: -0.0000

Data Index: 413446 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.4349. Min Act: -0.0000

Data Index: 442412 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.5842. Min Act: -0.0000

Data Index: 363360 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.5691. Min Act: -0.0000

Data Index: 2316 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.5160. Min Act: -0.0000

Data Index: 355620 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.6240. Min Act: -0.0000

Data Index: 690477 (C4 (Web Text))

Max Activating Token Index: 365

Text #15

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.2670. Min Act: -0.0000

Data Index: 1043553 (C4 (Web Text))

Max Activating Token Index: 228

Text #16

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.3728. Min Act: -0.0000

Data Index: 449877 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.3588. Min Act: -0.0000

Data Index: 915369 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.4898. Min Act: -0.0000

Data Index: 1128082 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 5.5696. Min Range: -5.5696

Max Act: 3.3396. Min Act: -0.0000

Data Index: 944473 (C4 (Web Text))

Max Activating Token Index: 365