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

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

Neuron 4172 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1230344 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.4972. Min Act: -0.0000

Data Index: 581981 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3730. Min Act: -0.0000

Data Index: 647119 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3677. Min Act: -0.0000

Data Index: 462406 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3886. Min Act: -0.0000

Data Index: 1085537 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3481. Min Act: -0.0000

Data Index: 810548 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3438. Min Act: -0.0000

Data Index: 281100 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3343. Min Act: -0.0000

Data Index: 974266 (C4 (Web Text))

Max Activating Token Index: 541

Text #8

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3286. Min Act: -0.0000

Data Index: 896163 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3215. Min Act: -0.0000

Data Index: 913979 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3188. Min Act: -0.0000

Data Index: 1310630 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3397. Min Act: -0.0000

Data Index: 935209 (C4 (Web Text))

Max Activating Token Index: 140

Text #12

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3030. Min Act: -0.0000

Data Index: 751017 (C4 (Web Text))

Max Activating Token Index: 232

Text #13

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1131053 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3019. Min Act: -0.0000

Data Index: 610927 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3011. Min Act: -0.0000

Data Index: 432273 (C4 (Web Text))

Max Activating Token Index: 153

Text #16

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.2978. Min Act: -0.0000

Data Index: 232539 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3080. Min Act: -0.0000

Data Index: 550158 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1271909 (C4 (Web Text))

Max Activating Token Index: 420

Text #19

Max Range: 0.5875. Min Range: -0.5875

Max Act: 0.3051. Min Act: -0.0000

Data Index: 9776 (C4 (Web Text))

Max Activating Token Index: 99