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

Dataset: The Pile

Neuron 4303 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0000

Data Index: 538325 (The Pile)

Max Activating Token Index: 72

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0251. Min Act: -0.0000

Data Index: 1353467 (The Pile)

Max Activating Token Index: 8

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0246. Min Act: 0.0000

Data Index: 1974238 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1431224 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0243. Min Act: -0.0000

Data Index: 1063769 (The Pile)

Max Activating Token Index: 48

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0240. Min Act: 0.0000

Data Index: 1058184 (The Pile)

Max Activating Token Index: 420

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0240. Min Act: -0.0000

Data Index: 1144746 (The Pile)

Max Activating Token Index: 8

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0238. Min Act: -0.0000

Data Index: 866420 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0244. Min Act: 0.0000

Data Index: 145766 (The Pile)

Max Activating Token Index: 322

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0235. Min Act: -0.0000

Data Index: 432533 (The Pile)

Max Activating Token Index: 377

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0234. Min Act: 0.0000

Data Index: 801702 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0233. Min Act: -0.0000

Data Index: 1831900 (The Pile)

Max Activating Token Index: 88

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0241. Min Act: -0.0000

Data Index: 594936 (The Pile)

Max Activating Token Index: 3

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0232. Min Act: 0.0000

Data Index: 707074 (The Pile)

Max Activating Token Index: 32

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0232. Min Act: 0.0000

Data Index: 1450552 (The Pile)

Max Activating Token Index: 1018

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0231. Min Act: -0.0000

Data Index: 1350004 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0231. Min Act: 0.0000

Data Index: 1243736 (The Pile)

Max Activating Token Index: 924

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0229. Min Act: 0.0000

Data Index: 1516216 (The Pile)

Max Activating Token Index: 562

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0228. Min Act: -0.0000

Data Index: 1763905 (The Pile)

Max Activating Token Index: 107

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0228. Min Act: 0.0000

Data Index: 1485126 (The Pile)

Max Activating Token Index: 67