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

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

Neuron 2834 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: 1.4180. Min Range: -1.4180

Max Act: 1.4180. Min Act: -0.0001

Data Index: 767259 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.3631. Min Act: -0.0001

Data Index: 1061035 (C4 (Web Text))

Max Activating Token Index: 887

Text #2

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.2490. Min Act: -0.0001

Data Index: 731072 (C4 (Web Text))

Max Activating Token Index: 421

Text #3

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.2433. Min Act: -0.0001

Data Index: 555041 (C4 (Web Text))

Max Activating Token Index: 912

Text #4

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.2590. Min Act: -0.0001

Data Index: 91644 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.1606. Min Act: -0.0001

Data Index: 313546 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.1345. Min Act: -0.0001

Data Index: 559862 (C4 (Web Text))

Max Activating Token Index: 897

Text #7

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0855. Min Act: -0.0001

Data Index: 168152 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.2057. Min Act: -0.0001

Data Index: 24541 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0691. Min Act: -0.0001

Data Index: 212792 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0379. Min Act: -0.0001

Data Index: 515154 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.2217. Min Act: -0.0001

Data Index: 524845 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0824. Min Act: -0.0001

Data Index: 791751 (C4 (Web Text))

Max Activating Token Index: 57

Text #13

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0922. Min Act: -0.0001

Data Index: 1343429 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0132. Min Act: -0.0001

Data Index: 138133 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0322. Min Act: -0.0001

Data Index: 1143092 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0124. Min Act: -0.0001

Data Index: 664235 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0615. Min Act: -0.0001

Data Index: 1209509 (C4 (Web Text))

Max Activating Token Index: 859

Text #18

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0300. Min Act: -0.0001

Data Index: 383946 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 1.4180. Min Range: -1.4180

Max Act: 1.0042. Min Act: -0.0001

Data Index: 241755 (C4 (Web Text))

Max Activating Token Index: 14