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

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

Neuron 2472 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.4110. Min Act: -0.0001

Data Index: 513233 (C4 (Web Text))

Max Activating Token Index: 781

Text #1

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3886. Min Act: -0.0001

Data Index: 1139674 (C4 (Web Text))

Max Activating Token Index: 252

Text #2

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3871. Min Act: -0.0001

Data Index: 897814 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3801. Min Act: -0.0001

Data Index: 750715 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3392. Min Act: -0.0001

Data Index: 59439 (C4 (Web Text))

Max Activating Token Index: 821

Text #5

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3519. Min Act: -0.0001

Data Index: 818327 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3359. Min Act: -0.0001

Data Index: 714004 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3321. Min Act: -0.0001

Data Index: 931432 (C4 (Web Text))

Max Activating Token Index: 86

Text #8

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3121. Min Act: -0.0001

Data Index: 951005 (C4 (Web Text))

Max Activating Token Index: 76

Text #9

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3303. Min Act: -0.0001

Data Index: 654950 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3173. Min Act: -0.0001

Data Index: 411563 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3125. Min Act: -0.0001

Data Index: 500876 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3280. Min Act: -0.0001

Data Index: 18323 (C4 (Web Text))

Max Activating Token Index: 610

Text #13

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3199. Min Act: -0.0001

Data Index: 437095 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.2841. Min Act: -0.0001

Data Index: 690448 (C4 (Web Text))

Max Activating Token Index: 806

Text #15

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3048. Min Act: -0.0001

Data Index: 454305 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3234. Min Act: -0.0001

Data Index: 412306 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3047. Min Act: -0.0001

Data Index: 882231 (C4 (Web Text))

Max Activating Token Index: 187

Text #18

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3285. Min Act: -0.0001

Data Index: 323773 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.4110. Min Range: -0.4110

Max Act: 0.3050. Min Act: -0.0001

Data Index: 1149076 (C4 (Web Text))

Max Activating Token Index: 11