Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5894 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.2925. Min Range: -6.2925

Max Act: 6.2925. Min Act: -0.0000

Data Index: 444117 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 6.2925. Min Range: -6.2925

Max Act: 5.3551. Min Act: -0.0000

Data Index: 1114211 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 6.2925. Min Range: -6.2925

Max Act: 5.0842. Min Act: -0.0000

Data Index: 893693 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 6.2925. Min Range: -6.2925

Max Act: 5.0373. Min Act: -0.0000

Data Index: 122007 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 6.2925. Min Range: -6.2925

Max Act: 4.0071. Min Act: -0.0000

Data Index: 282336 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 6.2925. Min Range: -6.2925

Max Act: 4.0036. Min Act: -0.0000

Data Index: 573313 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.8326. Min Act: -0.0000

Data Index: 1037274 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.9275. Min Act: -0.0000

Data Index: 479486 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 6.2925. Min Range: -6.2925

Max Act: 4.2161. Min Act: -0.0000

Data Index: 203482 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.8308. Min Act: -0.0000

Data Index: 221033 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.5200. Min Act: -0.0000

Data Index: 1345075 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.6423. Min Act: -0.0000

Data Index: 575974 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.5517. Min Act: -0.0000

Data Index: 400886 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.2429. Min Act: -0.0000

Data Index: 207137 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.1023. Min Act: -0.0000

Data Index: 432102 (C4 (Web Text))

Max Activating Token Index: 184

Text #15

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.0937. Min Act: -0.0000

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.1448. Min Act: -0.0000

Data Index: 646664 (C4 (Web Text))

Max Activating Token Index: 71

Text #17

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.2311. Min Act: -0.0000

Data Index: 471075 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.0917. Min Act: -0.0000

Data Index: 830194 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 6.2925. Min Range: -6.2925

Max Act: 3.0792. Min Act: -0.0000

Data Index: 809033 (C4 (Web Text))

Max Activating Token Index: 454