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

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

Neuron 1972 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4076. Min Act: -0.0001

Data Index: 535596 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4215. Min Act: -0.0001

Data Index: 827073 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4052. Min Act: -0.0001

Data Index: 505782 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.4223. Min Act: -0.0001

Data Index: 170696 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1323596 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3873. Min Act: -0.0001

Data Index: 308138 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3640. Min Act: -0.0001

Data Index: 411905 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3427. Min Act: -0.0001

Data Index: 674951 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3553. Min Act: -0.0001

Data Index: 2143 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3803. Min Act: -0.0001

Data Index: 388231 (C4 (Web Text))

Max Activating Token Index: 643

Text #10

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3536. Min Act: -0.0001

Data Index: 143754 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3517. Min Act: -0.0001

Data Index: 938626 (C4 (Web Text))

Max Activating Token Index: 837

Text #12

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3620. Min Act: -0.0001

Data Index: 1216529 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3622. Min Act: -0.0001

Data Index: 574504 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3363. Min Act: -0.0001

Data Index: 286517 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3262. Min Act: -0.0001

Data Index: 1328023 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3257. Min Act: -0.0001

Data Index: 1266093 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3343. Min Act: -0.0001

Data Index: 535329 (C4 (Web Text))

Max Activating Token Index: 404

Text #18

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3424. Min Act: -0.0001

Data Index: 427804 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 0.4223. Min Range: -0.4223

Max Act: 0.3329. Min Act: -0.0001

Data Index: 836994 (C4 (Web Text))

Max Activating Token Index: 215