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

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

Neuron 937 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.7452. Min Act: -0.0002

Data Index: 148798 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6318. Min Act: -0.0002

Data Index: 1029927 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6281. Min Act: -0.0002

Data Index: 260902 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6529. Min Act: -0.0002

Data Index: 350690 (C4 (Web Text))

Max Activating Token Index: 294

Text #4

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6363. Min Act: -0.0002

Data Index: 560398 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6392. Min Act: -0.0002

Data Index: 443214 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5638. Min Act: -0.0002

Data Index: 853163 (C4 (Web Text))

Max Activating Token Index: 951

Text #7

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6097. Min Act: -0.0002

Data Index: 423034 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5751. Min Act: -0.0002

Data Index: 1287896 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5275. Min Act: -0.0002

Data Index: 349646 (C4 (Web Text))

Max Activating Token Index: 101

Text #10

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5196. Min Act: -0.0002

Data Index: 473774 (C4 (Web Text))

Max Activating Token Index: 215

Text #11

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5581. Min Act: -0.0002

Data Index: 1174833 (C4 (Web Text))

Max Activating Token Index: 109

Text #12

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5943. Min Act: -0.0002

Data Index: 41281 (C4 (Web Text))

Max Activating Token Index: 566

Text #13

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6205. Min Act: -0.0002

Data Index: 1342640 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5840. Min Act: -0.0002

Data Index: 603992 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6018. Min Act: -0.0002

Data Index: 557809 (C4 (Web Text))

Max Activating Token Index: 230

Text #16

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6140. Min Act: -0.0002

Data Index: 22667 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.5950. Min Act: -0.0002

Data Index: 96612 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.4918. Min Act: -0.0002

Data Index: 592785 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.7452. Min Range: -0.7452

Max Act: 0.6339. Min Act: -0.0002

Data Index: 254446 (C4 (Web Text))

Max Activating Token Index: 503