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

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

Neuron 2720 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0001

Data Index: 1292978 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0263. Min Act: -0.0001

Data Index: 5908 (C4 (Web Text))

Max Activating Token Index: 536

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0250. Min Act: -0.0001

Data Index: 368995 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0269. Min Act: -0.0001

Data Index: 382808 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0276. Min Act: -0.0001

Data Index: 381107 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0246. Min Act: -0.0001

Data Index: 217131 (C4 (Web Text))

Max Activating Token Index: 459

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0252. Min Act: -0.0001

Data Index: 1287032 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1009214 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0219. Min Act: -0.0001

Data Index: 722404 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1211600 (C4 (Web Text))

Max Activating Token Index: 514

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0227. Min Act: -0.0001

Data Index: 1365594 (Python Code)

Max Activating Token Index: 591

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0239. Min Act: -0.0001

Data Index: 219933 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0227. Min Act: -0.0001

Data Index: 880180 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0215. Min Act: -0.0001

Data Index: 356807 (C4 (Web Text))

Max Activating Token Index: 543

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0215. Min Act: -0.0001

Data Index: 832714 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0220. Min Act: -0.0001

Data Index: 469949 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1393654 (Python Code)

Max Activating Token Index: 362

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0206. Min Act: -0.0001

Data Index: 612041 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0221. Min Act: -0.0001

Data Index: 518109 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0227. Min Act: -0.0001

Data Index: 686123 (C4 (Web Text))

Max Activating Token Index: 563