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

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

Neuron 2206 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1910. Min Act: -0.0000

Data Index: 279228 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1929. Min Act: -0.0001

Data Index: 215078 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1006388 (C4 (Web Text))

Max Activating Token Index: 765

Text #3

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1447. Min Act: -0.0000

Data Index: 581225 (C4 (Web Text))

Max Activating Token Index: 142

Text #4

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1489. Min Act: -0.0000

Data Index: 327179 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1440. Min Act: -0.0000

Data Index: 306025 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1393. Min Act: -0.0000

Data Index: 383748 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1401. Min Act: -0.0000

Data Index: 296380 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1314. Min Act: -0.0000

Data Index: 498338 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1360. Min Act: -0.0001

Data Index: 973163 (C4 (Web Text))

Max Activating Token Index: 922

Text #10

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1334. Min Act: -0.0000

Data Index: 217347 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1266. Min Act: -0.0001

Data Index: 44690 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1263. Min Act: -0.0000

Data Index: 837064 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1279. Min Act: -0.0001

Data Index: 606319 (C4 (Web Text))

Max Activating Token Index: 873

Text #14

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1269. Min Act: -0.0000

Data Index: 614162 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1225. Min Act: -0.0000

Data Index: 1358462 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1195. Min Act: -0.0001

Data Index: 1189067 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1153. Min Act: -0.0001

Data Index: 993994 (C4 (Web Text))

Max Activating Token Index: 745

Text #18

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1273. Min Act: -0.0000

Data Index: 285112 (C4 (Web Text))

Max Activating Token Index: 872

Text #19

Max Range: 0.1929. Min Range: -0.1929

Max Act: 0.1192. Min Act: -0.0000

Data Index: 991637 (C4 (Web Text))

Max Activating Token Index: 153