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

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

Neuron 205 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7982. Min Act: -0.0001

Data Index: 44358 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.7034. Min Act: -0.0001

Data Index: 1269206 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6749. Min Act: -0.0001

Data Index: 166993 (C4 (Web Text))

Max Activating Token Index: 1019

Text #3

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6139. Min Act: -0.0001

Data Index: 1208628 (C4 (Web Text))

Max Activating Token Index: 972

Text #4

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5753. Min Act: -0.0001

Data Index: 977317 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.6013. Min Act: -0.0001

Data Index: 49064 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5852. Min Act: -0.0001

Data Index: 870484 (C4 (Web Text))

Max Activating Token Index: 620

Text #7

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5501. Min Act: -0.0001

Data Index: 99647 (C4 (Web Text))

Max Activating Token Index: 222

Text #8

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5680. Min Act: -0.0001

Data Index: 818320 (C4 (Web Text))

Max Activating Token Index: 591

Text #9

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5270. Min Act: -0.0001

Data Index: 515993 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5735. Min Act: -0.0001

Data Index: 160355 (C4 (Web Text))

Max Activating Token Index: 470

Text #11

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5719. Min Act: -0.0001

Data Index: 1057522 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5110. Min Act: -0.0001

Data Index: 1212407 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1288320 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5174. Min Act: -0.0001

Data Index: 1022873 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5005. Min Act: -0.0001

Data Index: 393839 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4822. Min Act: -0.0001

Data Index: 357727 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4988. Min Act: -0.0001

Data Index: 880239 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.5029. Min Act: -0.0001

Data Index: 1135235 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 0.7982. Min Range: -0.7982

Max Act: 0.4984. Min Act: -0.0001

Data Index: 579935 (C4 (Web Text))

Max Activating Token Index: 73