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

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

Neuron 5121 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0001

Data Index: 52064 (C4 (Web Text))

Max Activating Token Index: 277

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1061. Min Act: -0.0001

Data Index: 844535 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1126. Min Act: -0.0001

Data Index: 762155 (C4 (Web Text))

Max Activating Token Index: 503

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1028. Min Act: -0.0001

Data Index: 1238264 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1151770 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1032. Min Act: -0.0001

Data Index: 1354865 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0906. Min Act: -0.0001

Data Index: 14156 (C4 (Web Text))

Max Activating Token Index: 964

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0931. Min Act: -0.0001

Data Index: 402028 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1186165 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1089761 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0975. Min Act: -0.0001

Data Index: 524713 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0962. Min Act: -0.0001

Data Index: 546972 (C4 (Web Text))

Max Activating Token Index: 566

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0779. Min Act: -0.0001

Data Index: 537950 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0868. Min Act: -0.0001

Data Index: 81348 (C4 (Web Text))

Max Activating Token Index: 492

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0918. Min Act: -0.0001

Data Index: 1352669 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0828. Min Act: -0.0001

Data Index: 1634456 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0916. Min Act: -0.0001

Data Index: 12733 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0925. Min Act: -0.0001

Data Index: 1505153 (Python Code)

Max Activating Token Index: 82

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0890. Min Act: -0.0001

Data Index: 219840 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0813. Min Act: -0.0001

Data Index: 948978 (C4 (Web Text))

Max Activating Token Index: 391