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

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

Neuron 1389 in Layer 7

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: 1521413 (Python Code)

Max Activating Token Index: 217

Text #1

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1474946 (Python Code)

Max Activating Token Index: 931

Text #2

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1486306 (Python Code)

Max Activating Token Index: 552

Text #3

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1618493 (Python Code)

Max Activating Token Index: 363

Text #4

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1373. Min Act: -0.0000

Data Index: 29748 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1407. Min Act: -0.0000

Data Index: 147369 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1519322 (Python Code)

Max Activating Token Index: 984

Text #7

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1082602 (C4 (Web Text))

Max Activating Token Index: 227

Text #8

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1314. Min Act: -0.0001

Data Index: 1561113 (Python Code)

Max Activating Token Index: 451

Text #9

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1520031 (Python Code)

Max Activating Token Index: 535

Text #10

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1321. Min Act: -0.0000

Data Index: 737595 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1264. Min Act: -0.0001

Data Index: 740848 (C4 (Web Text))

Max Activating Token Index: 271

Text #12

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1267. Min Act: -0.0001

Data Index: 1566598 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1319. Min Act: -0.0001

Data Index: 1525950 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1218. Min Act: -0.0001

Data Index: 1603941 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1302. Min Act: -0.0000

Data Index: 742767 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1249. Min Act: -0.0000

Data Index: 815136 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1222. Min Act: -0.0000

Data Index: 636585 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1631129 (Python Code)

Max Activating Token Index: 459

Text #19

Max Range: 0.1567. Min Range: -0.1567

Max Act: 0.1206. Min Act: -0.0001

Data Index: 1589082 (Python Code)

Max Activating Token Index: 57