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

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

Neuron 5128 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: 0.1407. Min Range: -0.1407

Max Act: 0.1290. Min Act: -0.0000

Data Index: 536196 (C4 (Web Text))

Max Activating Token Index: 1001

Text #1

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1407. Min Act: -0.0000

Data Index: 499029 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1192. Min Act: -0.0000

Data Index: 176455 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1218. Min Act: -0.0000

Data Index: 796027 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1131. Min Act: -0.0000

Data Index: 790124 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1136608 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1153. Min Act: -0.0000

Data Index: 775425 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1096. Min Act: -0.0000

Data Index: 917574 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1059. Min Act: -0.0000

Data Index: 296669 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0972. Min Act: -0.0000

Data Index: 268288 (C4 (Web Text))

Max Activating Token Index: 245

Text #10

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0946. Min Act: -0.0000

Data Index: 671870 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0966. Min Act: -0.0000

Data Index: 1052315 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0978. Min Act: -0.0000

Data Index: 780967 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1531965 (Python Code)

Max Activating Token Index: 330

Text #14

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0962. Min Act: -0.0000

Data Index: 409382 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0912. Min Act: -0.0000

Data Index: 810402 (C4 (Web Text))

Max Activating Token Index: 616

Text #16

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1296039 (C4 (Web Text))

Max Activating Token Index: 458

Text #17

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0926. Min Act: -0.0000

Data Index: 538557 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0862. Min Act: -0.0000

Data Index: 924465 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.1407. Min Range: -0.1407

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1133222 (C4 (Web Text))

Max Activating Token Index: 205