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

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

Neuron 1586 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2239. Min Range: -3.2239

Max Act: 3.2239. Min Act: -0.0000

Data Index: 879654 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 3.2239. Min Range: -3.2239

Max Act: 2.2047. Min Act: -0.0000

Data Index: 66346 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 3.2239. Min Range: -3.2239

Max Act: 2.1704. Min Act: -0.0000

Data Index: 272130 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 3.2239. Min Range: -3.2239

Max Act: 2.1242. Min Act: -0.0000

Data Index: 1350016 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9913. Min Act: -0.0000

Data Index: 592891 (C4 (Web Text))

Max Activating Token Index: 1002

Text #5

Max Range: 3.2239. Min Range: -3.2239

Max Act: 2.1824. Min Act: -0.0000

Data Index: 81144 (C4 (Web Text))

Max Activating Token Index: 667

Text #6

Max Range: 3.2239. Min Range: -3.2239

Max Act: 2.0431. Min Act: -0.0000

Data Index: 1057047 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9336. Min Act: -0.0000

Data Index: 1167619 (C4 (Web Text))

Max Activating Token Index: 184

Text #8

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9085. Min Act: -0.0000

Data Index: 796533 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 3.2239. Min Range: -3.2239

Max Act: 2.0200. Min Act: -0.0000

Data Index: 530248 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9769. Min Act: -0.0000

Data Index: 656632 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.7785. Min Act: -0.0000

Data Index: 815665 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9477. Min Act: -0.0000

Data Index: 1078894 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9567. Min Act: -0.0000

Data Index: 331793 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9406. Min Act: -0.0000

Data Index: 777767 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9092. Min Act: -0.0000

Data Index: 1013996 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.7698. Min Act: -0.0000

Data Index: 757367 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.9611. Min Act: -0.0000

Data Index: 751734 (C4 (Web Text))

Max Activating Token Index: 455

Text #18

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.7006. Min Act: -0.0000

Data Index: 957573 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 3.2239. Min Range: -3.2239

Max Act: 1.8073. Min Act: -0.0000

Data Index: 892392 (C4 (Web Text))

Max Activating Token Index: 925