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

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

Neuron 359 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.6270. Min Act: -0.0001

Data Index: 244468 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.7805. Min Act: -0.0000

Data Index: 397273 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.6732. Min Act: -0.0001

Data Index: 57229 (C4 (Web Text))

Max Activating Token Index: 763

Text #3

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.3392. Min Act: -0.0001

Data Index: 281681 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.4640. Min Act: -0.0001

Data Index: 739250 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.3851. Min Act: -0.0001

Data Index: 1042225 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.4457. Min Act: -0.0001

Data Index: 762260 (C4 (Web Text))

Max Activating Token Index: 523

Text #7

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.3621. Min Act: -0.0000

Data Index: 981793 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.2401. Min Act: -0.0001

Data Index: 705171 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.3838. Min Act: -0.0001

Data Index: 137325 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.1972. Min Act: -0.0001

Data Index: 131490 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1135660 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.1481. Min Act: -0.0001

Data Index: 948228 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.3803. Min Act: -0.0000

Data Index: 1169783 (C4 (Web Text))

Max Activating Token Index: 724

Text #14

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.4114. Min Act: -0.0001

Data Index: 287917 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.3668. Min Act: -0.0001

Data Index: 1255640 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.4234. Min Act: -0.0001

Data Index: 397292 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.2042. Min Act: -0.0001

Data Index: 516052 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.2765. Min Act: -0.0001

Data Index: 1194317 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 1.7805. Min Range: -1.7805

Max Act: 1.5755. Min Act: -0.0001

Data Index: 712012 (C4 (Web Text))

Max Activating Token Index: 893