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

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

Neuron 4044 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.6988. Min Act: -0.0001

Data Index: 478332 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.5363. Min Act: -0.0000

Data Index: 979651 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4959. Min Act: -0.0000

Data Index: 136037 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4643. Min Act: -0.0000

Data Index: 1203832 (C4 (Web Text))

Max Activating Token Index: 878

Text #4

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4391. Min Act: -0.0001

Data Index: 1100865 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4349. Min Act: -0.0000

Data Index: 58630 (C4 (Web Text))

Max Activating Token Index: 452

Text #6

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4404. Min Act: -0.0001

Data Index: 194475 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4249. Min Act: -0.0001

Data Index: 1025879 (C4 (Web Text))

Max Activating Token Index: 752

Text #8

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3952. Min Act: -0.0000

Data Index: 1296023 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4332. Min Act: -0.0001

Data Index: 466664 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4095. Min Act: -0.0000

Data Index: 1059012 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3919. Min Act: -0.0001

Data Index: 448003 (C4 (Web Text))

Max Activating Token Index: 862

Text #12

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4065. Min Act: -0.0000

Data Index: 197218 (C4 (Web Text))

Max Activating Token Index: 871

Text #13

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3898. Min Act: -0.0000

Data Index: 746502 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3898. Min Act: -0.0000

Data Index: 875020 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.4018. Min Act: -0.0000

Data Index: 561938 (C4 (Web Text))

Max Activating Token Index: 983

Text #16

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3996. Min Act: -0.0000

Data Index: 753900 (C4 (Web Text))

Max Activating Token Index: 877

Text #17

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3985. Min Act: -0.0001

Data Index: 1151365 (C4 (Web Text))

Max Activating Token Index: 352

Text #18

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1225235 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.6988. Min Range: -0.6988

Max Act: 0.3886. Min Act: -0.0000

Data Index: 324451 (C4 (Web Text))

Max Activating Token Index: 791