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

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

Neuron 1655 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2279. Min Act: -0.0003

Data Index: 300364 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2227. Min Act: -0.0003

Data Index: 771154 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2260. Min Act: -0.0002

Data Index: 180765 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2038. Min Act: -0.0003

Data Index: 889337 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2034. Min Act: -0.0003

Data Index: 227988 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.2081. Min Act: -0.0003

Data Index: 916538 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1916. Min Act: -0.0003

Data Index: 1339431 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1980. Min Act: -0.0002

Data Index: 100654 (C4 (Web Text))

Max Activating Token Index: 243

Text #8

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1979. Min Act: -0.0003

Data Index: 625083 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1954. Min Act: -0.0003

Data Index: 1116829 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1877. Min Act: -0.0003

Data Index: 1258256 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1939. Min Act: -0.0003

Data Index: 471342 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1860. Min Act: -0.0003

Data Index: 479969 (C4 (Web Text))

Max Activating Token Index: 94

Text #13

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1926. Min Act: -0.0003

Data Index: 1256648 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1903. Min Act: -0.0003

Data Index: 1158497 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1871. Min Act: -0.0003

Data Index: 1013036 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1849. Min Act: -0.0002

Data Index: 72586 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1893. Min Act: -0.0003

Data Index: 824987 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1862. Min Act: -0.0003

Data Index: 895020 (C4 (Web Text))

Max Activating Token Index: 1018

Text #19

Max Range: 0.2279. Min Range: -0.2279

Max Act: 0.1779. Min Act: -0.0003

Data Index: 1194165 (C4 (Web Text))

Max Activating Token Index: 512