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

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

Neuron 4545 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.8385. Min Act: -0.0000

Data Index: 285782 (C4 (Web Text))

Max Activating Token Index: 536

Text #1

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.8211. Min Act: -0.0000

Data Index: 223555 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.8087. Min Act: -0.0000

Data Index: 925056 (C4 (Web Text))

Max Activating Token Index: 929

Text #3

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6650. Min Act: -0.0000

Data Index: 990117 (C4 (Web Text))

Max Activating Token Index: 839

Text #4

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.7478. Min Act: -0.0000

Data Index: 587469 (C4 (Web Text))

Max Activating Token Index: 262

Text #5

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6819. Min Act: -0.0000

Data Index: 1241770 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6468. Min Act: -0.0000

Data Index: 117436 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5400. Min Act: -0.0000

Data Index: 71769 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5283. Min Act: -0.0000

Data Index: 714841 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5937. Min Act: -0.0000

Data Index: 743840 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6056. Min Act: -0.0000

Data Index: 842203 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.5856. Min Act: -0.0000

Data Index: 508767 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6505. Min Act: -0.0000

Data Index: 1147755 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.6257. Min Act: -0.0000

Data Index: 957509 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4123. Min Act: -0.0000

Data Index: 1308982 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4909. Min Act: -0.0000

Data Index: 535980 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4802. Min Act: -0.0000

Data Index: 1200069 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4752. Min Act: -0.0000

Data Index: 25721 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4616. Min Act: -0.0000

Data Index: 1296332 (C4 (Web Text))

Max Activating Token Index: 779

Text #19

Max Range: 1.8385. Min Range: -1.8385

Max Act: 1.4512. Min Act: -0.0000

Data Index: 682753 (C4 (Web Text))

Max Activating Token Index: 749