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

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

Neuron 1305 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.1982. Min Act: -0.0000

Data Index: 486476 (C4 (Web Text))

Max Activating Token Index: 329

Text #1

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0887. Min Act: -0.0000

Data Index: 817908 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 1.1982. Min Range: -1.1982

Max Act: 1.0067. Min Act: -0.0000

Data Index: 620966 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.9303. Min Act: -0.0000

Data Index: 1099400 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8233. Min Act: -0.0000

Data Index: 480897 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8896. Min Act: -0.0000

Data Index: 446524 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8152. Min Act: -0.0000

Data Index: 1089424 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8742. Min Act: -0.0000

Data Index: 1018786 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8608. Min Act: -0.0000

Data Index: 241347 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8851. Min Act: -0.0000

Data Index: 90007 (C4 (Web Text))

Max Activating Token Index: 877

Text #10

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8287. Min Act: -0.0000

Data Index: 1130340 (C4 (Web Text))

Max Activating Token Index: 878

Text #11

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1212520 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.7473. Min Act: -0.0000

Data Index: 995346 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8187. Min Act: -0.0000

Data Index: 147932 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8095. Min Act: -0.0000

Data Index: 243538 (C4 (Web Text))

Max Activating Token Index: 549

Text #15

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8342. Min Act: -0.0000

Data Index: 931980 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8268. Min Act: -0.0000

Data Index: 333037 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.7999. Min Act: -0.0000

Data Index: 235643 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.8296. Min Act: -0.0000

Data Index: 1017287 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 1.1982. Min Range: -1.1982

Max Act: 0.7602. Min Act: -0.0000

Data Index: 1230125 (C4 (Web Text))

Max Activating Token Index: 704