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

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

Neuron 4928 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.8134. Min Act: -0.0000

Data Index: 268286 (C4 (Web Text))

Max Activating Token Index: 409

Text #1

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.6918. Min Act: -0.0000

Data Index: 465939 (C4 (Web Text))

Max Activating Token Index: 922

Text #2

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5466. Min Act: -0.0000

Data Index: 363411 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.6347. Min Act: -0.0000

Data Index: 1338039 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.6083. Min Act: -0.0000

Data Index: 1266973 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5311. Min Act: -0.0000

Data Index: 300967 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5462. Min Act: -0.0000

Data Index: 1147567 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5544. Min Act: -0.0000

Data Index: 930200 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5831. Min Act: -0.0000

Data Index: 64215 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5703. Min Act: -0.0000

Data Index: 261526 (C4 (Web Text))

Max Activating Token Index: 407

Text #10

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5588. Min Act: -0.0000

Data Index: 1290231 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5292. Min Act: -0.0000

Data Index: 764611 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5262. Min Act: -0.0000

Data Index: 886086 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5484. Min Act: -0.0001

Data Index: 771296 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4974. Min Act: -0.0000

Data Index: 592014 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5412. Min Act: -0.0001

Data Index: 31683 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4973. Min Act: -0.0000

Data Index: 1300743 (C4 (Web Text))

Max Activating Token Index: 158

Text #17

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4804. Min Act: -0.0000

Data Index: 687114 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5307. Min Act: -0.0001

Data Index: 1112304 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5323. Min Act: -0.0000

Data Index: 141515 (C4 (Web Text))

Max Activating Token Index: 712