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

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

Neuron 2472 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.8147. Min Act: -0.0001

Data Index: 22238 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7215. Min Act: -0.0001

Data Index: 1193113 (C4 (Web Text))

Max Activating Token Index: 564

Text #2

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7771. Min Act: -0.0001

Data Index: 1086737 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7337. Min Act: -0.0001

Data Index: 102401 (C4 (Web Text))

Max Activating Token Index: 416

Text #4

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7662. Min Act: -0.0001

Data Index: 336511 (C4 (Web Text))

Max Activating Token Index: 610

Text #5

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7230. Min Act: -0.0001

Data Index: 705233 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.6978. Min Act: -0.0001

Data Index: 55821 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.6793. Min Act: -0.0001

Data Index: 587596 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.6799. Min Act: -0.0001

Data Index: 528506 (C4 (Web Text))

Max Activating Token Index: 245

Text #9

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7579. Min Act: -0.0001

Data Index: 561264 (C4 (Web Text))

Max Activating Token Index: 483

Text #10

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7164. Min Act: -0.0001

Data Index: 616015 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7621. Min Act: -0.0001

Data Index: 453510 (C4 (Web Text))

Max Activating Token Index: 227

Text #12

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7073. Min Act: -0.0001

Data Index: 372315 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.6772. Min Act: -0.0001

Data Index: 32566 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7567. Min Act: -0.0001

Data Index: 1040668 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.6519. Min Act: -0.0001

Data Index: 1316541 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7027. Min Act: -0.0001

Data Index: 252079 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.6434. Min Act: -0.0001

Data Index: 87786 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.7399. Min Act: -0.0001

Data Index: 224356 (C4 (Web Text))

Max Activating Token Index: 286

Text #19

Max Range: 0.8147. Min Range: -0.8147

Max Act: 0.6360. Min Act: -0.0001

Data Index: 307151 (C4 (Web Text))

Max Activating Token Index: 836