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

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

Neuron 5075 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2486. Min Act: -0.0001

Data Index: 198797 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2216. Min Act: -0.0001

Data Index: 273802 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2241. Min Act: -0.0001

Data Index: 348001 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1191838 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2192. Min Act: -0.0001

Data Index: 1037225 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2074. Min Act: -0.0001

Data Index: 600972 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2075. Min Act: -0.0001

Data Index: 1039170 (C4 (Web Text))

Max Activating Token Index: 325

Text #7

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1980. Min Act: -0.0001

Data Index: 1228732 (C4 (Web Text))

Max Activating Token Index: 849

Text #8

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2159. Min Act: -0.0001

Data Index: 829229 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2149. Min Act: -0.0001

Data Index: 1391843 (Python Code)

Max Activating Token Index: 3

Text #10

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2110. Min Act: -0.0001

Data Index: 1308584 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2006. Min Act: -0.0001

Data Index: 1259537 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1979. Min Act: -0.0001

Data Index: 95243 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1890. Min Act: -0.0001

Data Index: 802950 (C4 (Web Text))

Max Activating Token Index: 728

Text #14

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.2147. Min Act: -0.0001

Data Index: 992712 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1962. Min Act: -0.0001

Data Index: 262008 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1885. Min Act: -0.0001

Data Index: 302769 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1916. Min Act: -0.0001

Data Index: 83224 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1949. Min Act: -0.0001

Data Index: 1149241 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.2486. Min Range: -0.2486

Max Act: 0.1798. Min Act: -0.0001

Data Index: 314878 (C4 (Web Text))

Max Activating Token Index: 229