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

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

Neuron 3546 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1328581 (C4 (Web Text))

Max Activating Token Index: 502

Text #1

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0238. Min Act: -0.0003

Data Index: 145900 (C4 (Web Text))

Max Activating Token Index: 756

Text #2

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0206. Min Act: -0.0003

Data Index: 885906 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0184. Min Act: -0.0003

Data Index: 429737 (C4 (Web Text))

Max Activating Token Index: 797

Text #4

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1021441 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1066541 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1212562 (C4 (Web Text))

Max Activating Token Index: 965

Text #7

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0176. Min Act: -0.0003

Data Index: 157103 (C4 (Web Text))

Max Activating Token Index: 980

Text #8

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0173. Min Act: -0.0003

Data Index: 459686 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0188. Min Act: -0.0004

Data Index: 1007706 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0171. Min Act: -0.0003

Data Index: 905953 (C4 (Web Text))

Max Activating Token Index: 772

Text #11

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0175. Min Act: -0.0003

Data Index: 553246 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0164. Min Act: -0.0003

Data Index: 966498 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1143864 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0166. Min Act: -0.0004

Data Index: 775278 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0164. Min Act: -0.0003

Data Index: 656803 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1315469 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1113320 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0160. Min Act: -0.0003

Data Index: 204429 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0253. Min Range: -0.0253

Max Act: 0.0173. Min Act: -0.0003

Data Index: 522253 (C4 (Web Text))

Max Activating Token Index: 400