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

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

Neuron 2694 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: 0.5491. Min Range: -0.5491

Max Act: 0.5491. Min Act: -0.0000

Data Index: 1104846 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.5283. Min Act: -0.0000

Data Index: 40187 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4630. Min Act: -0.0001

Data Index: 138774 (C4 (Web Text))

Max Activating Token Index: 729

Text #3

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4642. Min Act: -0.0000

Data Index: 378708 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4545. Min Act: -0.0001

Data Index: 774912 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1277014 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4167. Min Act: -0.0001

Data Index: 708042 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4072. Min Act: -0.0000

Data Index: 848289 (C4 (Web Text))

Max Activating Token Index: 57

Text #8

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4007. Min Act: -0.0001

Data Index: 100447 (C4 (Web Text))

Max Activating Token Index: 382

Text #9

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3975. Min Act: -0.0001

Data Index: 1265267 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3649. Min Act: -0.0000

Data Index: 1131628 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3912. Min Act: -0.0001

Data Index: 592299 (C4 (Web Text))

Max Activating Token Index: 18

Text #12

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3896. Min Act: -0.0001

Data Index: 505104 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.4147. Min Act: -0.0000

Data Index: 444107 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3853. Min Act: -0.0000

Data Index: 859442 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3840. Min Act: -0.0000

Data Index: 27278 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3676. Min Act: -0.0000

Data Index: 36181 (C4 (Web Text))

Max Activating Token Index: 56

Text #17

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3779. Min Act: -0.0000

Data Index: 548731 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3905. Min Act: -0.0000

Data Index: 150865 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.5491. Min Range: -0.5491

Max Act: 0.3772. Min Act: -0.0000

Data Index: 25478 (C4 (Web Text))

Max Activating Token Index: 70