Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3915 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.9863. Min Act: -0.0002

Data Index: 39030 (C4 (Web Text))

Max Activating Token Index: 134

Text #1

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.9388. Min Act: -0.0002

Data Index: 109191 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.8019. Min Act: -0.0002

Data Index: 544098 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6933. Min Act: -0.0002

Data Index: 1293875 (C4 (Web Text))

Max Activating Token Index: 348

Text #4

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6729. Min Act: -0.0002

Data Index: 164578 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6282. Min Act: -0.0002

Data Index: 131781 (C4 (Web Text))

Max Activating Token Index: 433

Text #6

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6360. Min Act: -0.0002

Data Index: 440919 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6159. Min Act: -0.0002

Data Index: 196124 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6309. Min Act: -0.0002

Data Index: 880539 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6019. Min Act: -0.0002

Data Index: 95019 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5992. Min Act: -0.0002

Data Index: 1139841 (C4 (Web Text))

Max Activating Token Index: 77

Text #11

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6125. Min Act: -0.0002

Data Index: 206555 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5932. Min Act: -0.0002

Data Index: 207446 (C4 (Web Text))

Max Activating Token Index: 180

Text #13

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6080. Min Act: -0.0002

Data Index: 61904 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6090. Min Act: -0.0002

Data Index: 672656 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.6013. Min Act: -0.0002

Data Index: 453897 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5618. Min Act: -0.0002

Data Index: 12037 (C4 (Web Text))

Max Activating Token Index: 929

Text #17

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5459. Min Act: -0.0002

Data Index: 1338641 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5945. Min Act: -0.0002

Data Index: 717851 (C4 (Web Text))

Max Activating Token Index: 753

Text #19

Max Range: 0.9863. Min Range: -0.9863

Max Act: 0.5733. Min Act: -0.0002

Data Index: 36576 (C4 (Web Text))

Max Activating Token Index: 60