Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2542 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.7948. Min Act: -0.0000

Data Index: 600894 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1492704 (Python Code)

Max Activating Token Index: 589

Text #2

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6361. Min Act: -0.0000

Data Index: 543008 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1619771 (Python Code)

Max Activating Token Index: 484

Text #4

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6440. Min Act: -0.0000

Data Index: 979022 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5789. Min Act: -0.0000

Data Index: 1527280 (Python Code)

Max Activating Token Index: 355

Text #6

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5752. Min Act: -0.0000

Data Index: 263456 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.6117. Min Act: -0.0000

Data Index: 149518 (C4 (Web Text))

Max Activating Token Index: 718

Text #8

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5642. Min Act: -0.0000

Data Index: 1476402 (Python Code)

Max Activating Token Index: 788

Text #9

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5734. Min Act: -0.0000

Data Index: 1074091 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5313. Min Act: -0.0000

Data Index: 762895 (C4 (Web Text))

Max Activating Token Index: 23

Text #11

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5527. Min Act: -0.0000

Data Index: 230732 (C4 (Web Text))

Max Activating Token Index: 252

Text #12

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5387. Min Act: -0.0000

Data Index: 488488 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5335. Min Act: -0.0000

Data Index: 322195 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5205. Min Act: -0.0000

Data Index: 1419818 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5294. Min Act: -0.0000

Data Index: 496724 (C4 (Web Text))

Max Activating Token Index: 188

Text #16

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1165265 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1324483 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5124. Min Act: -0.0000

Data Index: 1228740 (C4 (Web Text))

Max Activating Token Index: 119

Text #19

Max Range: 0.7948. Min Range: -0.7948

Max Act: 0.5098. Min Act: -0.0000

Data Index: 886201 (C4 (Web Text))

Max Activating Token Index: 939