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

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

Neuron 2668 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.9063. Min Act: -0.0001

Data Index: 436883 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.8911. Min Act: -0.0001

Data Index: 159711 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.8181. Min Act: -0.0001

Data Index: 699801 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.8585. Min Act: -0.0001

Data Index: 653323 (C4 (Web Text))

Max Activating Token Index: 461

Text #4

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.8206. Min Act: -0.0001

Data Index: 753858 (C4 (Web Text))

Max Activating Token Index: 575

Text #5

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7220. Min Act: -0.0001

Data Index: 769575 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7811. Min Act: -0.0001

Data Index: 835695 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7288. Min Act: -0.0002

Data Index: 379512 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7711. Min Act: -0.0002

Data Index: 200669 (C4 (Web Text))

Max Activating Token Index: 250

Text #9

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.6958. Min Act: -0.0001

Data Index: 1345330 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7408. Min Act: -0.0001

Data Index: 845823 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7368. Min Act: -0.0002

Data Index: 93707 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7339. Min Act: -0.0002

Data Index: 539647 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7278. Min Act: -0.0001

Data Index: 771162 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.6591. Min Act: -0.0001

Data Index: 918019 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7507. Min Act: -0.0001

Data Index: 757842 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7458. Min Act: -0.0001

Data Index: 108584 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7391. Min Act: -0.0002

Data Index: 582466 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.6920. Min Act: -0.0002

Data Index: 1187511 (C4 (Web Text))

Max Activating Token Index: 330

Text #19

Max Range: 0.9063. Min Range: -0.9063

Max Act: 0.7369. Min Act: -0.0002

Data Index: 1272000 (C4 (Web Text))

Max Activating Token Index: 928