Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1709 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.5267. Min Act: -0.0000

Data Index: 733198 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1191369 (C4 (Web Text))

Max Activating Token Index: 1018

Text #2

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1713. Min Act: -0.0000

Data Index: 160684 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1054. Min Act: -0.0000

Data Index: 647537 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0886. Min Act: -0.0000

Data Index: 944689 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1481. Min Act: -0.0000

Data Index: 976257 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1407. Min Act: -0.0000

Data Index: 1008268 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1329. Min Act: -0.0000

Data Index: 808224 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1264. Min Act: -0.0000

Data Index: 523629 (C4 (Web Text))

Max Activating Token Index: 270

Text #9

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1306. Min Act: -0.0000

Data Index: 349636 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0578. Min Act: -0.0000

Data Index: 546392 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1198. Min Act: -0.0000

Data Index: 138675 (C4 (Web Text))

Max Activating Token Index: 10

Text #12

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1060. Min Act: -0.0000

Data Index: 1100190 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0912. Min Act: -0.0000

Data Index: 410329 (C4 (Web Text))

Max Activating Token Index: 629

Text #14

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0918. Min Act: -0.0000

Data Index: 498433 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1514. Min Act: -0.0000

Data Index: 1046707 (C4 (Web Text))

Max Activating Token Index: 793

Text #16

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0058. Min Act: -0.0000

Data Index: 914858 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.1395. Min Act: -0.0000

Data Index: 1249941 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0707. Min Act: -0.0000

Data Index: 857551 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 1.5267. Min Range: -1.5267

Max Act: 1.0764. Min Act: -0.0000

Data Index: 221119 (C4 (Web Text))

Max Activating Token Index: 807