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

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

Neuron 5832 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: 0.1866. Min Range: -0.1866

Max Act: 0.1866. Min Act: -0.0000

Data Index: 525000 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1653. Min Act: -0.0000

Data Index: 1310112 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1637. Min Act: -0.0000

Data Index: 382449 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1684. Min Act: -0.0000

Data Index: 416469 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1511. Min Act: -0.0000

Data Index: 1349638 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1449. Min Act: 0.0000

Data Index: 1074409 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1368. Min Act: -0.0000

Data Index: 11220 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1382. Min Act: -0.0000

Data Index: 787215 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1225268 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1323. Min Act: -0.0000

Data Index: 546976 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1220. Min Act: -0.0000

Data Index: 525668 (C4 (Web Text))

Max Activating Token Index: 899

Text #11

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1281. Min Act: -0.0000

Data Index: 119030 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1193. Min Act: -0.0000

Data Index: 518491 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1229. Min Act: 0.0000

Data Index: 1103700 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1257. Min Act: -0.0000

Data Index: 999929 (C4 (Web Text))

Max Activating Token Index: 55

Text #15

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1130. Min Act: -0.0000

Data Index: 971263 (C4 (Web Text))

Max Activating Token Index: 191

Text #16

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1179. Min Act: -0.0000

Data Index: 956367 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1165. Min Act: -0.0000

Data Index: 772560 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1120641 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.1866. Min Range: -0.1866

Max Act: 0.1103. Min Act: -0.0000

Data Index: 652604 (C4 (Web Text))

Max Activating Token Index: 656