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

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

Neuron 2976 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: 1.7223. Min Range: -1.7223

Max Act: 1.7223. Min Act: -0.0000

Data Index: 789327 (C4 (Web Text))

Max Activating Token Index: 764

Text #1

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.3890. Min Act: -0.0000

Data Index: 1074223 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.4356. Min Act: -0.0000

Data Index: 1175598 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.3359. Min Act: -0.0000

Data Index: 528616 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.3164. Min Act: -0.0000

Data Index: 1184614 (C4 (Web Text))

Max Activating Token Index: 117

Text #5

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.2549. Min Act: -0.0000

Data Index: 1274732 (C4 (Web Text))

Max Activating Token Index: 419

Text #6

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.2561. Min Act: -0.0000

Data Index: 741388 (C4 (Web Text))

Max Activating Token Index: 202

Text #7

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1087544 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.2026. Min Act: -0.0000

Data Index: 435748 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.3053. Min Act: -0.0000

Data Index: 1101997 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1117956 (C4 (Web Text))

Max Activating Token Index: 94

Text #11

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.2286. Min Act: -0.0000

Data Index: 889779 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1855. Min Act: -0.0000

Data Index: 787101 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1850. Min Act: -0.0000

Data Index: 712861 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1497. Min Act: -0.0000

Data Index: 76899 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1282. Min Act: -0.0000

Data Index: 871074 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1162. Min Act: -0.0000

Data Index: 877052 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1033. Min Act: -0.0000

Data Index: 175596 (C4 (Web Text))

Max Activating Token Index: 897

Text #18

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1227. Min Act: -0.0000

Data Index: 952297 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 1.7223. Min Range: -1.7223

Max Act: 1.1116. Min Act: -0.0000

Data Index: 1495985 (Python Code)

Max Activating Token Index: 277