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

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

Neuron 3768 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1586541 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2723. Min Act: -0.0000

Data Index: 1384706 (Python Code)

Max Activating Token Index: 23

Text #2

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2609. Min Act: -0.0000

Data Index: 1471955 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1370970 (Python Code)

Max Activating Token Index: 1002

Text #4

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2584. Min Act: -0.0000

Data Index: 1422236 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2452. Min Act: -0.0000

Data Index: 1380064 (Python Code)

Max Activating Token Index: 553

Text #6

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1464617 (Python Code)

Max Activating Token Index: 578

Text #7

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2270. Min Act: -0.0000

Data Index: 1557672 (Python Code)

Max Activating Token Index: 705

Text #8

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1612795 (Python Code)

Max Activating Token Index: 52

Text #9

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2272. Min Act: -0.0000

Data Index: 1629655 (Python Code)

Max Activating Token Index: 858

Text #10

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2266. Min Act: -0.0000

Data Index: 1606563 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2257. Min Act: -0.0000

Data Index: 1366406 (Python Code)

Max Activating Token Index: 148

Text #12

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1598431 (Python Code)

Max Activating Token Index: 691

Text #13

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2424. Min Act: -0.0000

Data Index: 1374926 (Python Code)

Max Activating Token Index: 772

Text #14

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1396827 (Python Code)

Max Activating Token Index: 779

Text #15

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2199. Min Act: -0.0000

Data Index: 1590290 (Python Code)

Max Activating Token Index: 999

Text #16

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1556621 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2250. Min Act: -0.0000

Data Index: 1444393 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2170. Min Act: -0.0000

Data Index: 1383273 (Python Code)

Max Activating Token Index: 385

Text #19

Max Range: 0.3045. Min Range: -0.3045

Max Act: 0.2341. Min Act: -0.0000

Data Index: 1389683 (Python Code)

Max Activating Token Index: 975