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

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

Neuron 221 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1814. Min Act: -0.0001

Data Index: 418110 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1521. Min Act: -0.0000

Data Index: 398358 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1492. Min Act: -0.0000

Data Index: 260857 (C4 (Web Text))

Max Activating Token Index: 253

Text #3

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1117350 (C4 (Web Text))

Max Activating Token Index: 536

Text #4

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1507. Min Act: -0.0001

Data Index: 22975 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1412. Min Act: -0.0000

Data Index: 528936 (C4 (Web Text))

Max Activating Token Index: 980

Text #6

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1343. Min Act: -0.0000

Data Index: 405045 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1306. Min Act: -0.0000

Data Index: 253812 (C4 (Web Text))

Max Activating Token Index: 723

Text #8

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1265. Min Act: -0.0000

Data Index: 972387 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1308. Min Act: -0.0000

Data Index: 725476 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1306. Min Act: -0.0000

Data Index: 338231 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1344354 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1200. Min Act: -0.0000

Data Index: 517482 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1247. Min Act: -0.0001

Data Index: 486060 (C4 (Web Text))

Max Activating Token Index: 40

Text #14

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1329. Min Act: -0.0001

Data Index: 864716 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1168. Min Act: -0.0000

Data Index: 878041 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1202. Min Act: -0.0000

Data Index: 1059125 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1153703 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1172. Min Act: -0.0000

Data Index: 823899 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.1814. Min Range: -0.1814

Max Act: 0.1198. Min Act: -0.0001

Data Index: 809256 (C4 (Web Text))

Max Activating Token Index: 870