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

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

Neuron 4399 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6748. Min Act: -0.0000

Data Index: 304719 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6521. Min Act: -0.0000

Data Index: 104884 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6135. Min Act: -0.0000

Data Index: 320864 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6241. Min Act: -0.0000

Data Index: 837081 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.6045. Min Act: -0.0000

Data Index: 547267 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1028280 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5631. Min Act: -0.0000

Data Index: 704389 (C4 (Web Text))

Max Activating Token Index: 64

Text #7

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5788. Min Act: -0.0000

Data Index: 720795 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5409. Min Act: -0.0000

Data Index: 142464 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5414. Min Act: -0.0000

Data Index: 425403 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5560. Min Act: -0.0000

Data Index: 217179 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5530. Min Act: -0.0000

Data Index: 398427 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5259. Min Act: -0.0000

Data Index: 791373 (C4 (Web Text))

Max Activating Token Index: 184

Text #13

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5550. Min Act: -0.0000

Data Index: 1272965 (C4 (Web Text))

Max Activating Token Index: 1000

Text #14

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5488. Min Act: 0.0000

Data Index: 165061 (C4 (Web Text))

Max Activating Token Index: 761

Text #15

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5424. Min Act: -0.0000

Data Index: 136359 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5645. Min Act: -0.0000

Data Index: 609963 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1251906 (C4 (Web Text))

Max Activating Token Index: 1014

Text #18

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.4953. Min Act: -0.0000

Data Index: 976079 (C4 (Web Text))

Max Activating Token Index: 531

Text #19

Max Range: 0.6748. Min Range: -0.6748

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1006541 (C4 (Web Text))

Max Activating Token Index: 256