Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1114 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0413. Min Act: -0.0002

Data Index: 57660 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1294001 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0360. Min Act: -0.0002

Data Index: 273330 (C4 (Web Text))

Max Activating Token Index: 789

Text #3

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1441382 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1072124 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1620626 (Python Code)

Max Activating Token Index: 480

Text #6

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0259. Min Act: -0.0002

Data Index: 149482 (C4 (Web Text))

Max Activating Token Index: 449

Text #7

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1630346 (Python Code)

Max Activating Token Index: 295

Text #8

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1366139 (Python Code)

Max Activating Token Index: 13

Text #9

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1383568 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1381926 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0231. Min Act: -0.0002

Data Index: 160843 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1408712 (Python Code)

Max Activating Token Index: 7

Text #13

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0232. Min Act: -0.0002

Data Index: 1493090 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1545987 (Python Code)

Max Activating Token Index: 32

Text #15

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1552495 (Python Code)

Max Activating Token Index: 520

Text #16

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1612734 (Python Code)

Max Activating Token Index: 24

Text #17

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1630175 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0219. Min Act: -0.0002

Data Index: 1582380 (Python Code)

Max Activating Token Index: 834

Text #19

Max Range: 0.0413. Min Range: -0.0413

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1647251 (Python Code)

Max Activating Token Index: 807