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

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

Neuron 606 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0512. Min Act: -0.0005

Data Index: 599504 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0327. Min Act: -0.0005

Data Index: 454761 (C4 (Web Text))

Max Activating Token Index: 867

Text #2

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0328. Min Act: -0.0005

Data Index: 946235 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0383. Min Act: -0.0005

Data Index: 1329376 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0305. Min Act: -0.0005

Data Index: 642192 (C4 (Web Text))

Max Activating Token Index: 766

Text #5

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0311. Min Act: -0.0005

Data Index: 958061 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0309. Min Act: -0.0005

Data Index: 129896 (C4 (Web Text))

Max Activating Token Index: 409

Text #7

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0298. Min Act: -0.0005

Data Index: 952486 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0268. Min Act: -0.0005

Data Index: 429285 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0294. Min Act: -0.0005

Data Index: 79547 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0274. Min Act: -0.0005

Data Index: 307826 (C4 (Web Text))

Max Activating Token Index: 117

Text #11

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0255. Min Act: -0.0005

Data Index: 665960 (C4 (Web Text))

Max Activating Token Index: 215

Text #12

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0293. Min Act: -0.0005

Data Index: 51458 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0274. Min Act: -0.0005

Data Index: 911459 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0283. Min Act: -0.0005

Data Index: 668170 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1208370 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0290. Min Act: -0.0004

Data Index: 1222510 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0278. Min Act: -0.0005

Data Index: 857231 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0242. Min Act: -0.0005

Data Index: 1214267 (C4 (Web Text))

Max Activating Token Index: 968

Text #19

Max Range: 0.0512. Min Range: -0.0512

Max Act: 0.0261. Min Act: -0.0005

Data Index: 302116 (C4 (Web Text))

Max Activating Token Index: 335