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

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

Neuron 2877 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.8924. Min Act: -0.0000

Data Index: 210045 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.6717. Min Act: -0.0000

Data Index: 1034163 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.7945. Min Act: -0.0000

Data Index: 1076084 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.6421. Min Act: -0.0000

Data Index: 726779 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.6214. Min Act: -0.0000

Data Index: 498732 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.3324. Min Act: -0.0000

Data Index: 194604 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.4204. Min Act: -0.0000

Data Index: 647876 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.3863. Min Act: -0.0000

Data Index: 957572 (C4 (Web Text))

Max Activating Token Index: 499

Text #8

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.5434. Min Act: -0.0000

Data Index: 491167 (C4 (Web Text))

Max Activating Token Index: 498

Text #9

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.2765. Min Act: -0.0000

Data Index: 973241 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.2684. Min Act: -0.0000

Data Index: 324811 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.5189. Min Act: -0.0000

Data Index: 983515 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.0262. Min Act: -0.0000

Data Index: 1028028 (C4 (Web Text))

Max Activating Token Index: 721

Text #13

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.1785. Min Act: -0.0000

Data Index: 1042268 (C4 (Web Text))

Max Activating Token Index: 419

Text #14

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.0445. Min Act: -0.0000

Data Index: 391172 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.1476. Min Act: -0.0000

Data Index: 1202356 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.5101. Min Act: -0.0000

Data Index: 1349491 (C4 (Web Text))

Max Activating Token Index: 361

Text #17

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.0014. Min Act: -0.0000

Data Index: 450586 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 2.8924. Min Range: -2.8924

Max Act: 1.9969. Min Act: -0.0000

Data Index: 277472 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 2.8924. Min Range: -2.8924

Max Act: 2.0463. Min Act: -0.0000

Data Index: 1265518 (C4 (Web Text))

Max Activating Token Index: 306