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

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

Neuron 1934 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6954. Min Range: -3.6954

Max Act: 3.6954. Min Act: -0.0000

Data Index: 284181 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 3.6954. Min Range: -3.6954

Max Act: 3.6209. Min Act: -0.0000

Data Index: 19482 (C4 (Web Text))

Max Activating Token Index: 736

Text #2

Max Range: 3.6954. Min Range: -3.6954

Max Act: 3.2154. Min Act: -0.0000

Data Index: 1050783 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 3.6954. Min Range: -3.6954

Max Act: 3.1902. Min Act: -0.0000

Data Index: 102446 (C4 (Web Text))

Max Activating Token Index: 899

Text #4

Max Range: 3.6954. Min Range: -3.6954

Max Act: 3.1476. Min Act: -0.0000

Data Index: 1073710 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 3.6954. Min Range: -3.6954

Max Act: 3.0456. Min Act: -0.0000

Data Index: 710854 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.7178. Min Act: -0.0000

Data Index: 442493 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.9060. Min Act: -0.0000

Data Index: 782771 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 3.6954. Min Range: -3.6954

Max Act: 3.0099. Min Act: -0.0000

Data Index: 100552 (C4 (Web Text))

Max Activating Token Index: 227

Text #9

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.8571. Min Act: -0.0000

Data Index: 79053 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.8630. Min Act: -0.0000

Data Index: 815479 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.6942. Min Act: -0.0000

Data Index: 742235 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.8216. Min Act: -0.0000

Data Index: 39196 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.8051. Min Act: -0.0000

Data Index: 225479 (C4 (Web Text))

Max Activating Token Index: 761

Text #14

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.6733. Min Act: -0.0000

Data Index: 626483 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.9176. Min Act: -0.0000

Data Index: 26460 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.7704. Min Act: -0.0000

Data Index: 1357085 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.5967. Min Act: -0.0000

Data Index: 1340962 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.7266. Min Act: -0.0000

Data Index: 448642 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 3.6954. Min Range: -3.6954

Max Act: 2.7243. Min Act: -0.0000

Data Index: 1249770 (C4 (Web Text))

Max Activating Token Index: 378