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

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

Neuron 1912 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0678. Min Range: -1.0678

Max Act: 1.0678. Min Act: -0.0000

Data Index: 72912 (C4 (Web Text))

Max Activating Token Index: 564

Text #1

Max Range: 1.0678. Min Range: -1.0678

Max Act: 1.0332. Min Act: -0.0000

Data Index: 469125 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.0678. Min Range: -1.0678

Max Act: 1.0406. Min Act: -0.0000

Data Index: 817799 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 1.0678. Min Range: -1.0678

Max Act: 1.0320. Min Act: -0.0000

Data Index: 963377 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.9578. Min Act: -0.0000

Data Index: 690269 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.9328. Min Act: -0.0000

Data Index: 1000042 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.9272. Min Act: -0.0000

Data Index: 999578 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8895. Min Act: -0.0000

Data Index: 309500 (C4 (Web Text))

Max Activating Token Index: 998

Text #8

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8977. Min Act: -0.0000

Data Index: 687431 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8830. Min Act: -0.0000

Data Index: 560550 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8033. Min Act: -0.0000

Data Index: 98751 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1183314 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8178. Min Act: -0.0000

Data Index: 1275876 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8227. Min Act: -0.0000

Data Index: 440583 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8408. Min Act: -0.0000

Data Index: 281928 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8511. Min Act: -0.0000

Data Index: 1099690 (C4 (Web Text))

Max Activating Token Index: 431

Text #16

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8469. Min Act: -0.0000

Data Index: 463588 (C4 (Web Text))

Max Activating Token Index: 146

Text #17

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.9041. Min Act: -0.0000

Data Index: 504989 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8237. Min Act: -0.0000

Data Index: 698629 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 1.0678. Min Range: -1.0678

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1306887 (C4 (Web Text))

Max Activating Token Index: 625