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

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

Neuron 4950 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: 7.7696. Min Range: -7.7696

Max Act: 7.7696. Min Act: -0.0000

Data Index: 35409 (C4 (Web Text))

Max Activating Token Index: 542

Text #1

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.3340. Min Act: -0.0000

Data Index: 1081379 (C4 (Web Text))

Max Activating Token Index: 182

Text #2

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.4454. Min Act: -0.0000

Data Index: 552369 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.3390. Min Act: -0.0000

Data Index: 663450 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.3385. Min Act: -0.0000

Data Index: 276319 (C4 (Web Text))

Max Activating Token Index: 234

Text #5

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.3149. Min Act: -0.0000

Data Index: 460393 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.3095. Min Act: -0.0000

Data Index: 209497 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.2474. Min Act: -0.0000

Data Index: 731040 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.1960. Min Act: -0.0000

Data Index: 1244971 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.1890. Min Act: -0.0000

Data Index: 633176 (C4 (Web Text))

Max Activating Token Index: 311

Text #10

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.0130. Min Act: -0.0000

Data Index: 1258575 (C4 (Web Text))

Max Activating Token Index: 885

Text #11

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.0872. Min Act: -0.0000

Data Index: 382834 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.0506. Min Act: -0.0000

Data Index: 1265293 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.0414. Min Act: -0.0000

Data Index: 881725 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 7.7696. Min Range: -7.7696

Max Act: 6.9909. Min Act: -0.0000

Data Index: 703471 (C4 (Web Text))

Max Activating Token Index: 406

Text #15

Max Range: 7.7696. Min Range: -7.7696

Max Act: 6.9276. Min Act: -0.0000

Data Index: 32492 (C4 (Web Text))

Max Activating Token Index: 888

Text #16

Max Range: 7.7696. Min Range: -7.7696

Max Act: 6.9348. Min Act: -0.0000

Data Index: 1316618 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 7.7696. Min Range: -7.7696

Max Act: 7.2704. Min Act: -0.0000

Data Index: 449669 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 7.7696. Min Range: -7.7696

Max Act: 6.6615. Min Act: -0.0000

Data Index: 282268 (C4 (Web Text))

Max Activating Token Index: 189

Text #19

Max Range: 7.7696. Min Range: -7.7696

Max Act: 6.8957. Min Act: -0.0000

Data Index: 823650 (C4 (Web Text))

Max Activating Token Index: 933