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

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

Neuron 3568 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: 1.4243. Min Range: -1.4243

Max Act: 1.3310. Min Act: -0.0000

Data Index: 419694 (C4 (Web Text))

Max Activating Token Index: 861

Text #1

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1252262 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.3268. Min Act: -0.0000

Data Index: 1149828 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.4243. Min Act: -0.0000

Data Index: 770901 (C4 (Web Text))

Max Activating Token Index: 13

Text #4

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.3354. Min Act: -0.0000

Data Index: 1299128 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.1945. Min Act: -0.0000

Data Index: 1095413 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.1363. Min Act: -0.0000

Data Index: 126069 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.1332. Min Act: -0.0000

Data Index: 1187643 (C4 (Web Text))

Max Activating Token Index: 296

Text #8

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.9229. Min Act: -0.0000

Data Index: 488133 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1203196 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.0506. Min Act: -0.0000

Data Index: 1249416 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.0446. Min Act: -0.0000

Data Index: 1263124 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.7855. Min Act: -0.0000

Data Index: 42561 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.9275. Min Act: -0.0000

Data Index: 225680 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.0283. Min Act: -0.0000

Data Index: 892036 (C4 (Web Text))

Max Activating Token Index: 556

Text #15

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.9550. Min Act: -0.0000

Data Index: 672967 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1177784 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 1.4243. Min Range: -1.4243

Max Act: 1.0112. Min Act: -0.0000

Data Index: 562836 (C4 (Web Text))

Max Activating Token Index: 1002

Text #18

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.9988. Min Act: -0.0000

Data Index: 558505 (C4 (Web Text))

Max Activating Token Index: 407

Text #19

Max Range: 1.4243. Min Range: -1.4243

Max Act: 0.9759. Min Act: -0.0000

Data Index: 674063 (C4 (Web Text))

Max Activating Token Index: 567