Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4809 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3317. Min Act: -0.0000

Data Index: 6842 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2856. Min Act: -0.0000

Data Index: 128561 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2982. Min Act: -0.0000

Data Index: 729620 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3000. Min Act: -0.0000

Data Index: 1574934 (Python Code)

Max Activating Token Index: 96

Text #4

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.3010. Min Act: -0.0000

Data Index: 239981 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2724. Min Act: -0.0000

Data Index: 575345 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2973. Min Act: -0.0000

Data Index: 887877 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2583. Min Act: -0.0000

Data Index: 5570 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2823. Min Act: -0.0000

Data Index: 136592 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2799. Min Act: -0.0000

Data Index: 767116 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2574. Min Act: -0.0000

Data Index: 691813 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2658. Min Act: -0.0000

Data Index: 357472 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2554. Min Act: -0.0000

Data Index: 1128102 (C4 (Web Text))

Max Activating Token Index: 357

Text #13

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2629. Min Act: -0.0000

Data Index: 599391 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2415. Min Act: -0.0000

Data Index: 633501 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2488. Min Act: -0.0000

Data Index: 785062 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1227757 (C4 (Web Text))

Max Activating Token Index: 850

Text #17

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2369. Min Act: -0.0000

Data Index: 1109972 (C4 (Web Text))

Max Activating Token Index: 655

Text #18

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2117. Min Act: -0.0000

Data Index: 193470 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.3317. Min Range: -0.3317

Max Act: 0.2378. Min Act: -0.0000

Data Index: 103127 (C4 (Web Text))

Max Activating Token Index: 652