Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1592 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2925. Min Act: -0.0003

Data Index: 1366407 (Python Code)

Max Activating Token Index: 766

Text #1

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2769. Min Act: -0.0003

Data Index: 1371709 (Python Code)

Max Activating Token Index: 208

Text #2

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2771. Min Act: -0.0003

Data Index: 1412629 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2473. Min Act: -0.0003

Data Index: 1497156 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2590. Min Act: -0.0003

Data Index: 1545676 (Python Code)

Max Activating Token Index: 172

Text #5

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2344. Min Act: -0.0003

Data Index: 1571120 (Python Code)

Max Activating Token Index: 125

Text #6

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2524. Min Act: -0.0003

Data Index: 1505556 (Python Code)

Max Activating Token Index: 149

Text #7

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2301. Min Act: -0.0003

Data Index: 1494322 (Python Code)

Max Activating Token Index: 133

Text #8

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2246. Min Act: -0.0003

Data Index: 1581033 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2272. Min Act: -0.0003

Data Index: 1486211 (Python Code)

Max Activating Token Index: 457

Text #10

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2304. Min Act: -0.0003

Data Index: 1521271 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2357. Min Act: -0.0003

Data Index: 1429709 (Python Code)

Max Activating Token Index: 1022

Text #12

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.1891. Min Act: -0.0003

Data Index: 1570105 (Python Code)

Max Activating Token Index: 605

Text #13

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2423. Min Act: -0.0003

Data Index: 1505377 (Python Code)

Max Activating Token Index: 953

Text #14

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2255. Min Act: -0.0003

Data Index: 1482281 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2244. Min Act: -0.0003

Data Index: 1561608 (Python Code)

Max Activating Token Index: 428

Text #16

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2158. Min Act: -0.0003

Data Index: 1566656 (Python Code)

Max Activating Token Index: 243

Text #17

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2169. Min Act: -0.0003

Data Index: 1590434 (Python Code)

Max Activating Token Index: 643

Text #18

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2311. Min Act: -0.0003

Data Index: 1418421 (Python Code)

Max Activating Token Index: 149

Text #19

Max Range: 0.2925. Min Range: -0.2925

Max Act: 0.2019. Min Act: -0.0003

Data Index: 1365131 (Python Code)

Max Activating Token Index: 387