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

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

Neuron 1586 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: 1.1221. Min Range: -1.1221

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1343350 (C4 (Web Text))

Max Activating Token Index: 453

Text #1

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9270. Min Act: -0.0000

Data Index: 561264 (C4 (Web Text))

Max Activating Token Index: 322

Text #2

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9446. Min Act: -0.0000

Data Index: 950189 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1193113 (C4 (Web Text))

Max Activating Token Index: 409

Text #4

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.9558. Min Act: -0.0000

Data Index: 102401 (C4 (Web Text))

Max Activating Token Index: 258

Text #5

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1122563 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8522. Min Act: -0.0000

Data Index: 587596 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8523. Min Act: -0.0000

Data Index: 616015 (C4 (Web Text))

Max Activating Token Index: 297

Text #8

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8039. Min Act: -0.0000

Data Index: 291715 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8466. Min Act: -0.0000

Data Index: 1213130 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8516. Min Act: -0.0000

Data Index: 114317 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.8356. Min Act: -0.0000

Data Index: 1334233 (C4 (Web Text))

Max Activating Token Index: 355

Text #12

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7829. Min Act: -0.0000

Data Index: 224356 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7857. Min Act: -0.0000

Data Index: 1302188 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1121429 (C4 (Web Text))

Max Activating Token Index: 963

Text #15

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7991. Min Act: -0.0000

Data Index: 126895 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7503. Min Act: -0.0000

Data Index: 336560 (C4 (Web Text))

Max Activating Token Index: 574

Text #17

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1193809 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7464. Min Act: -0.0000

Data Index: 570583 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 1.1221. Min Range: -1.1221

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1056229 (C4 (Web Text))

Max Activating Token Index: 274