Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2001 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1511200 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1403. Min Act: -0.0002

Data Index: 406748 (C4 (Web Text))

Max Activating Token Index: 1002

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1292. Min Act: -0.0002

Data Index: 555810 (C4 (Web Text))

Max Activating Token Index: 996

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1474301 (Python Code)

Max Activating Token Index: 762

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1289. Min Act: -0.0001

Data Index: 1399687 (Python Code)

Max Activating Token Index: 269

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1545050 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1251. Min Act: -0.0001

Data Index: 1518350 (Python Code)

Max Activating Token Index: 505

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1329. Min Act: -0.0001

Data Index: 357488 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1321. Min Act: -0.0001

Data Index: 334603 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1019418 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1271. Min Act: -0.0001

Data Index: 1501118 (Python Code)

Max Activating Token Index: 953

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1301. Min Act: -0.0001

Data Index: 976193 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1306. Min Act: -0.0001

Data Index: 49424 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1569340 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1133942 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1229. Min Act: -0.0001

Data Index: 284788 (C4 (Web Text))

Max Activating Token Index: 500

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1237. Min Act: -0.0001

Data Index: 968316 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1334062 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1177. Min Act: -0.0001

Data Index: 616993 (C4 (Web Text))

Max Activating Token Index: 977

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1350. Min Act: -0.0001

Data Index: 198060 (C4 (Web Text))

Max Activating Token Index: 977