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

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

Neuron 5990 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2196. Min Act: -0.0001

Data Index: 667798 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2464. Min Act: -0.0002

Data Index: 1291670 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2179. Min Act: -0.0001

Data Index: 963856 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2089. Min Act: -0.0001

Data Index: 448418 (C4 (Web Text))

Max Activating Token Index: 560

Text #4

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1943. Min Act: -0.0001

Data Index: 1043514 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1986. Min Act: -0.0001

Data Index: 1159311 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1845. Min Act: -0.0001

Data Index: 346699 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2077. Min Act: -0.0001

Data Index: 295338 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1031267 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.2001. Min Act: -0.0001

Data Index: 437711 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1869. Min Act: -0.0001

Data Index: 594868 (C4 (Web Text))

Max Activating Token Index: 797

Text #11

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1813. Min Act: -0.0001

Data Index: 408599 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1790. Min Act: -0.0001

Data Index: 570834 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1804. Min Act: -0.0001

Data Index: 15683 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1776. Min Act: -0.0001

Data Index: 60430 (C4 (Web Text))

Max Activating Token Index: 88

Text #15

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1949. Min Act: -0.0001

Data Index: 721612 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1941. Min Act: -0.0001

Data Index: 332638 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1662. Min Act: -0.0001

Data Index: 1090208 (C4 (Web Text))

Max Activating Token Index: 634

Text #18

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1617. Min Act: -0.0001

Data Index: 714752 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.2464. Min Range: -0.2464

Max Act: 0.1722. Min Act: -0.0001

Data Index: 712716 (C4 (Web Text))

Max Activating Token Index: 387