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

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

Neuron 2067 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: 0.9236. Min Range: -0.9236

Max Act: 0.8005. Min Act: -0.0002

Data Index: 682378 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8426. Min Act: -0.0002

Data Index: 28757 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.9102. Min Act: -0.0002

Data Index: 577201 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.9236. Min Act: -0.0002

Data Index: 1064422 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8016. Min Act: -0.0002

Data Index: 641390 (C4 (Web Text))

Max Activating Token Index: 698

Text #5

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7780. Min Act: -0.0001

Data Index: 790830 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8716. Min Act: -0.0001

Data Index: 965092 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8909. Min Act: -0.0002

Data Index: 408180 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7877. Min Act: -0.0001

Data Index: 116090 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8349. Min Act: -0.0002

Data Index: 108663 (C4 (Web Text))

Max Activating Token Index: 99

Text #10

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8075. Min Act: -0.0001

Data Index: 719075 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7856. Min Act: -0.0001

Data Index: 600712 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8342. Min Act: -0.0001

Data Index: 488348 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.8225. Min Act: -0.0002

Data Index: 20368 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7356. Min Act: -0.0002

Data Index: 943059 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7517. Min Act: -0.0002

Data Index: 348812 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7414. Min Act: -0.0001

Data Index: 1181239 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7010. Min Act: -0.0002

Data Index: 331338 (C4 (Web Text))

Max Activating Token Index: 135

Text #18

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7233. Min Act: -0.0002

Data Index: 433600 (C4 (Web Text))

Max Activating Token Index: 63

Text #19

Max Range: 0.9236. Min Range: -0.9236

Max Act: 0.7346. Min Act: -0.0002

Data Index: 90530 (C4 (Web Text))

Max Activating Token Index: 135