Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4500 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6643. Min Act: -0.0000

Data Index: 914779 (C4 (Web Text))

Max Activating Token Index: 348

Text #1

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6106. Min Act: -0.0000

Data Index: 782920 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5317. Min Act: -0.0000

Data Index: 727421 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1320298 (C4 (Web Text))

Max Activating Token Index: 738

Text #4

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1262307 (C4 (Web Text))

Max Activating Token Index: 751

Text #5

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.6250. Min Act: -0.0000

Data Index: 93167 (C4 (Web Text))

Max Activating Token Index: 358

Text #6

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5582. Min Act: -0.0000

Data Index: 949625 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5297. Min Act: -0.0000

Data Index: 491222 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5235. Min Act: -0.0000

Data Index: 30537 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5178. Min Act: -0.0000

Data Index: 692671 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5257. Min Act: -0.0000

Data Index: 451297 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1012285 (C4 (Web Text))

Max Activating Token Index: 778

Text #12

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5053. Min Act: -0.0000

Data Index: 661664 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1316729 (C4 (Web Text))

Max Activating Token Index: 616

Text #14

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4972. Min Act: -0.0000

Data Index: 13249 (C4 (Web Text))

Max Activating Token Index: 652

Text #15

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1299494 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1290394 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4337. Min Act: -0.0000

Data Index: 1352207 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1134522 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.6643. Min Range: -0.6643

Max Act: 0.4539. Min Act: -0.0000

Data Index: 776406 (C4 (Web Text))

Max Activating Token Index: 803