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

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

Neuron 1808 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: 0.2415. Min Range: -0.2415

Max Act: 0.2281. Min Act: -0.0000

Data Index: 138314 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2370. Min Act: -0.0000

Data Index: 361107 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2415. Min Act: -0.0001

Data Index: 217140 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1270993 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1247513 (C4 (Web Text))

Max Activating Token Index: 675

Text #5

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2100. Min Act: -0.0000

Data Index: 646531 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2042. Min Act: -0.0000

Data Index: 326798 (C4 (Web Text))

Max Activating Token Index: 767

Text #7

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.2078. Min Act: -0.0000

Data Index: 191206 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1661. Min Act: -0.0000

Data Index: 567232 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1247. Min Act: -0.0001

Data Index: 777975 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1241. Min Act: -0.0001

Data Index: 336125 (C4 (Web Text))

Max Activating Token Index: 660

Text #11

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1255. Min Act: -0.0001

Data Index: 146709 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1351. Min Act: -0.0001

Data Index: 616494 (C4 (Web Text))

Max Activating Token Index: 803

Text #13

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1254. Min Act: -0.0000

Data Index: 531179 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1066879 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1211. Min Act: -0.0000

Data Index: 427155 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1015815 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1196. Min Act: -0.0000

Data Index: 1222766 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1194. Min Act: -0.0001

Data Index: 628660 (C4 (Web Text))

Max Activating Token Index: 436

Text #19

Max Range: 0.2415. Min Range: -0.2415

Max Act: 0.1137. Min Act: -0.0000

Data Index: 635257 (C4 (Web Text))

Max Activating Token Index: 995