Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1799 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0363. Min Act: -0.0005

Data Index: 1438398 (Python Code)

Max Activating Token Index: 26

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0364. Min Act: -0.0005

Data Index: 1557942 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0005

Data Index: 1585172 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0350. Min Act: -0.0005

Data Index: 1523597 (Python Code)

Max Activating Token Index: 26

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0332. Min Act: -0.0005

Data Index: 1468157 (Python Code)

Max Activating Token Index: 33

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0307. Min Act: -0.0005

Data Index: 1485336 (Python Code)

Max Activating Token Index: 45

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1490963 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0309. Min Act: -0.0005

Data Index: 1366502 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0309. Min Act: -0.0005

Data Index: 1539292 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0313. Min Act: -0.0005

Data Index: 1656423 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0307. Min Act: -0.0005

Data Index: 1565991 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0306. Min Act: -0.0005

Data Index: 1516394 (Python Code)

Max Activating Token Index: 20

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1399557 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0304. Min Act: -0.0005

Data Index: 1529273 (Python Code)

Max Activating Token Index: 47

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0308. Min Act: -0.0005

Data Index: 1387721 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0301. Min Act: -0.0005

Data Index: 1621248 (Python Code)

Max Activating Token Index: 15

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0302. Min Act: -0.0005

Data Index: 1522165 (Python Code)

Max Activating Token Index: 27

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0300. Min Act: -0.0005

Data Index: 1451599 (Python Code)

Max Activating Token Index: 11

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0300. Min Act: -0.0005

Data Index: 1446324 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0298. Min Act: -0.0005

Data Index: 1395663 (Python Code)

Max Activating Token Index: 480