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

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

Neuron 2743 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: 1.1924. Min Range: -1.1924

Max Act: 1.1924. Min Act: -0.0000

Data Index: 720491 (C4 (Web Text))

Max Activating Token Index: 602

Text #1

Max Range: 1.1924. Min Range: -1.1924

Max Act: 1.0253. Min Act: -0.0000

Data Index: 487307 (C4 (Web Text))

Max Activating Token Index: 630

Text #2

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.9150. Min Act: 0.0000

Data Index: 1324507 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.8803. Min Act: 0.0001

Data Index: 997774 (C4 (Web Text))

Max Activating Token Index: 367

Text #4

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1351978 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.8787. Min Act: -0.0000

Data Index: 1110219 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.8048. Min Act: -0.0000

Data Index: 621879 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.8604. Min Act: -0.0000

Data Index: 1092579 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.8342. Min Act: -0.0000

Data Index: 360477 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.8218. Min Act: 0.0000

Data Index: 920300 (C4 (Web Text))

Max Activating Token Index: 147

Text #10

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7532. Min Act: -0.0000

Data Index: 846285 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7944. Min Act: 0.0000

Data Index: 747728 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7919. Min Act: -0.0000

Data Index: 1206432 (C4 (Web Text))

Max Activating Token Index: 662

Text #13

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7938. Min Act: 0.0000

Data Index: 1203948 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7886. Min Act: 0.0000

Data Index: 455596 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1176023 (C4 (Web Text))

Max Activating Token Index: 927

Text #16

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7513. Min Act: 0.0000

Data Index: 647737 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7027. Min Act: -0.0000

Data Index: 438830 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1134571 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 1.1924. Min Range: -1.1924

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1090597 (C4 (Web Text))

Max Activating Token Index: 821