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

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

Neuron 2498 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2481. Min Act: -0.0000

Data Index: 482573 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2386. Min Act: -0.0001

Data Index: 1537465 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1029669 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2136. Min Act: -0.0000

Data Index: 900524 (C4 (Web Text))

Max Activating Token Index: 115

Text #4

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2209. Min Act: -0.0000

Data Index: 1405959 (Python Code)

Max Activating Token Index: 95

Text #5

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2183. Min Act: -0.0001

Data Index: 533745 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1579721 (Python Code)

Max Activating Token Index: 84

Text #7

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2070. Min Act: -0.0001

Data Index: 1509970 (Python Code)

Max Activating Token Index: 963

Text #8

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2064. Min Act: -0.0001

Data Index: 837217 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1866. Min Act: -0.0000

Data Index: 1457284 (Python Code)

Max Activating Token Index: 789

Text #10

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2063. Min Act: -0.0000

Data Index: 185179 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2056. Min Act: -0.0001

Data Index: 1468913 (Python Code)

Max Activating Token Index: 999

Text #12

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1895. Min Act: -0.0001

Data Index: 1364761 (Python Code)

Max Activating Token Index: 947

Text #13

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2018. Min Act: -0.0000

Data Index: 902769 (C4 (Web Text))

Max Activating Token Index: 376

Text #14

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2027. Min Act: -0.0001

Data Index: 1223013 (C4 (Web Text))

Max Activating Token Index: 705

Text #15

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.2016. Min Act: -0.0000

Data Index: 1490910 (Python Code)

Max Activating Token Index: 727

Text #16

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1889. Min Act: -0.0000

Data Index: 984525 (C4 (Web Text))

Max Activating Token Index: 407

Text #17

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1858. Min Act: -0.0001

Data Index: 574755 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1892. Min Act: -0.0000

Data Index: 1637048 (Python Code)

Max Activating Token Index: 919

Text #19

Max Range: 0.2481. Min Range: -0.2481

Max Act: 0.1856. Min Act: -0.0001

Data Index: 63746 (C4 (Web Text))

Max Activating Token Index: 915