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

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

Neuron 3259 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: 0.7983. Min Range: -0.7983

Max Act: 0.7983. Min Act: -0.0000

Data Index: 1067767 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7703. Min Act: -0.0001

Data Index: 584202 (C4 (Web Text))

Max Activating Token Index: 431

Text #2

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7286. Min Act: -0.0000

Data Index: 1290825 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7012. Min Act: -0.0000

Data Index: 648992 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6349. Min Act: -0.0000

Data Index: 704231 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1077686 (C4 (Web Text))

Max Activating Token Index: 852

Text #6

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6289. Min Act: -0.0000

Data Index: 535803 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6210. Min Act: -0.0000

Data Index: 1033984 (C4 (Web Text))

Max Activating Token Index: 95

Text #8

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6080. Min Act: -0.0000

Data Index: 1094280 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5885. Min Act: -0.0001

Data Index: 751559 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6480. Min Act: -0.0001

Data Index: 72885 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6020. Min Act: -0.0001

Data Index: 1244549 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1102095 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5678. Min Act: -0.0000

Data Index: 191811 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5870. Min Act: -0.0000

Data Index: 268097 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5752. Min Act: -0.0000

Data Index: 925225 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5549. Min Act: -0.0001

Data Index: 1014714 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5543. Min Act: -0.0001

Data Index: 178247 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5711. Min Act: -0.0001

Data Index: 1339391 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 0.7983. Min Range: -0.7983

Max Act: 0.5910. Min Act: -0.0000

Data Index: 782215 (C4 (Web Text))

Max Activating Token Index: 154