Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1555 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6359. Min Act: -0.0002

Data Index: 484803 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.6327. Min Act: -0.0001

Data Index: 752147 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5790. Min Act: -0.0002

Data Index: 108734 (C4 (Web Text))

Max Activating Token Index: 660

Text #3

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5199. Min Act: -0.0002

Data Index: 617286 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5258. Min Act: -0.0002

Data Index: 253039 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5544. Min Act: -0.0002

Data Index: 866425 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5081. Min Act: -0.0002

Data Index: 822240 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5103. Min Act: -0.0002

Data Index: 613989 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5403. Min Act: -0.0002

Data Index: 578010 (C4 (Web Text))

Max Activating Token Index: 198

Text #9

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4822. Min Act: -0.0002

Data Index: 497891 (C4 (Web Text))

Max Activating Token Index: 962

Text #10

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5145. Min Act: -0.0002

Data Index: 263368 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5394. Min Act: -0.0002

Data Index: 1213634 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5126. Min Act: -0.0002

Data Index: 374619 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5072. Min Act: -0.0002

Data Index: 534760 (C4 (Web Text))

Max Activating Token Index: 561

Text #14

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5012. Min Act: -0.0002

Data Index: 720752 (C4 (Web Text))

Max Activating Token Index: 420

Text #15

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5099. Min Act: -0.0002

Data Index: 1275687 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5298. Min Act: -0.0001

Data Index: 812089 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5223. Min Act: -0.0002

Data Index: 402854 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.5199. Min Act: -0.0002

Data Index: 267637 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.6359. Min Range: -0.6359

Max Act: 0.4878. Min Act: -0.0002

Data Index: 1094738 (C4 (Web Text))

Max Activating Token Index: 916