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

Dataset: The Pile

Neuron 3815 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0000

Data Index: 1077791 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0214. Min Act: -0.0000

Data Index: 421020 (The Pile)

Max Activating Token Index: 188

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0221. Min Act: -0.0000

Data Index: 954935 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0219. Min Act: 0.0000

Data Index: 1369903 (The Pile)

Max Activating Token Index: 33

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0213. Min Act: -0.0000

Data Index: 596700 (The Pile)

Max Activating Token Index: 50

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0211. Min Act: 0.0000

Data Index: 1533753 (The Pile)

Max Activating Token Index: 613

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0206. Min Act: 0.0000

Data Index: 1317109 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0205. Min Act: 0.0000

Data Index: 1961914 (The Pile)

Max Activating Token Index: 155

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0203. Min Act: -0.0000

Data Index: 1456343 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0199. Min Act: -0.0001

Data Index: 1853387 (The Pile)

Max Activating Token Index: 17

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0202. Min Act: 0.0000

Data Index: 1185504 (The Pile)

Max Activating Token Index: 26

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0202. Min Act: -0.0000

Data Index: 422290 (The Pile)

Max Activating Token Index: 156

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0201. Min Act: -0.0000

Data Index: 503569 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0200. Min Act: -0.0000

Data Index: 1262822 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0191. Min Act: -0.0000

Data Index: 1781481 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0198. Min Act: 0.0000

Data Index: 1502228 (The Pile)

Max Activating Token Index: 42

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0197. Min Act: -0.0000

Data Index: 373624 (The Pile)

Max Activating Token Index: 37

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0197. Min Act: -0.0000

Data Index: 366376 (The Pile)

Max Activating Token Index: 60

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0196. Min Act: 0.0000

Data Index: 947427 (The Pile)

Max Activating Token Index: 81

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0194. Min Act: -0.0000

Data Index: 1625283 (The Pile)

Max Activating Token Index: 37