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

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

Neuron 2425 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: 0.1897. Min Range: -0.1897

Max Act: 0.1897. Min Act: -0.0000

Data Index: 161721 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1632. Min Act: -0.0000

Data Index: 73727 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1684. Min Act: -0.0000

Data Index: 527734 (C4 (Web Text))

Max Activating Token Index: 993

Text #3

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1623. Min Act: -0.0000

Data Index: 901751 (C4 (Web Text))

Max Activating Token Index: 471

Text #4

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1679. Min Act: 0.0000

Data Index: 297565 (C4 (Web Text))

Max Activating Token Index: 849

Text #5

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1201975 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1552. Min Act: -0.0000

Data Index: 210811 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1501. Min Act: -0.0000

Data Index: 765541 (C4 (Web Text))

Max Activating Token Index: 438

Text #8

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1475. Min Act: -0.0000

Data Index: 318956 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1308. Min Act: -0.0000

Data Index: 148814 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1328. Min Act: -0.0000

Data Index: 912336 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1282. Min Act: -0.0000

Data Index: 766362 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1327. Min Act: -0.0000

Data Index: 229037 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1316. Min Act: -0.0000

Data Index: 989125 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1207. Min Act: -0.0000

Data Index: 15002 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1194. Min Act: -0.0000

Data Index: 510180 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1248. Min Act: -0.0000

Data Index: 22315 (C4 (Web Text))

Max Activating Token Index: 910

Text #17

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1219. Min Act: -0.0000

Data Index: 31834 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1203. Min Act: 0.0000

Data Index: 1112810 (C4 (Web Text))

Max Activating Token Index: 500

Text #19

Max Range: 0.1897. Min Range: -0.1897

Max Act: 0.1245. Min Act: -0.0000

Data Index: 488192 (C4 (Web Text))

Max Activating Token Index: 1019