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

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

Neuron 4628 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0459. Min Range: -1.0459

Max Act: 1.0459. Min Act: -0.0000

Data Index: 838945 (C4 (Web Text))

Max Activating Token Index: 1016

Text #1

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.9641. Min Act: -0.0000

Data Index: 904210 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.9557. Min Act: -0.0000

Data Index: 303029 (C4 (Web Text))

Max Activating Token Index: 350

Text #3

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.9315. Min Act: -0.0000

Data Index: 730461 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.9661. Min Act: -0.0000

Data Index: 182957 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.9983. Min Act: -0.0000

Data Index: 1237643 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1087656 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1020466 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1288929 (C4 (Web Text))

Max Activating Token Index: 750

Text #9

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.9129. Min Act: -0.0000

Data Index: 710135 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8618. Min Act: -0.0000

Data Index: 41476 (C4 (Web Text))

Max Activating Token Index: 864

Text #11

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.7374. Min Act: -0.0000

Data Index: 1102987 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1343065 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1288910 (C4 (Web Text))

Max Activating Token Index: 229

Text #14

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.7756. Min Act: -0.0000

Data Index: 1212653 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1192450 (C4 (Web Text))

Max Activating Token Index: 744

Text #16

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1175797 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.6535. Min Act: -0.0000

Data Index: 612941 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8060. Min Act: -0.0000

Data Index: 629559 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.0459. Min Range: -1.0459

Max Act: 0.8050. Min Act: -0.0000

Data Index: 504247 (C4 (Web Text))

Max Activating Token Index: 764