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

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

Neuron 2130 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: 0.1610. Min Range: -0.1610

Max Act: 0.1610. Min Act: -0.0000

Data Index: 733555 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1532. Min Act: -0.0000

Data Index: 637856 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1339. Min Act: -0.0000

Data Index: 429002 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1366. Min Act: -0.0001

Data Index: 902699 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1319. Min Act: -0.0000

Data Index: 293960 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1302. Min Act: -0.0000

Data Index: 777899 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1260. Min Act: -0.0000

Data Index: 130349 (C4 (Web Text))

Max Activating Token Index: 438

Text #7

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1288. Min Act: -0.0000

Data Index: 903559 (C4 (Web Text))

Max Activating Token Index: 954

Text #8

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1260. Min Act: -0.0000

Data Index: 1275945 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1292. Min Act: -0.0000

Data Index: 243221 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1248. Min Act: -0.0000

Data Index: 617868 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1123909 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1149713 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1120. Min Act: -0.0000

Data Index: 910689 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1216. Min Act: -0.0000

Data Index: 458702 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1162. Min Act: -0.0000

Data Index: 18379 (C4 (Web Text))

Max Activating Token Index: 297

Text #16

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1164. Min Act: -0.0001

Data Index: 400630 (C4 (Web Text))

Max Activating Token Index: 272

Text #17

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1170. Min Act: -0.0000

Data Index: 638847 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1166. Min Act: -0.0001

Data Index: 503755 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.1610. Min Range: -0.1610

Max Act: 0.1203. Min Act: -0.0000

Data Index: 195966 (C4 (Web Text))

Max Activating Token Index: 180