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

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

Neuron 5748 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6862. Min Range: -4.6862

Max Act: 4.6862. Min Act: -0.0000

Data Index: 50323 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 4.6862. Min Range: -4.6862

Max Act: 4.5293. Min Act: -0.0000

Data Index: 730129 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 4.6862. Min Range: -4.6862

Max Act: 4.1322. Min Act: -0.0000

Data Index: 350491 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.8058. Min Act: -0.0000

Data Index: 87661 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.6607. Min Act: -0.0000

Data Index: 321 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.4638. Min Act: -0.0000

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 735

Text #6

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.7733. Min Act: -0.0000

Data Index: 305032 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.7388. Min Act: -0.0001

Data Index: 444612 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.8802. Min Act: -0.0000

Data Index: 350604 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.6672. Min Act: -0.0000

Data Index: 434865 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.6182. Min Act: -0.0001

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.7743. Min Act: -0.0000

Data Index: 543803 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.4368. Min Act: -0.0000

Data Index: 356630 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.5764. Min Act: -0.0000

Data Index: 126307 (C4 (Web Text))

Max Activating Token Index: 341

Text #14

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.3636. Min Act: -0.0000

Data Index: 632631 (C4 (Web Text))

Max Activating Token Index: 58

Text #15

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.5001. Min Act: -0.0000

Data Index: 87402 (C4 (Web Text))

Max Activating Token Index: 420

Text #16

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.4459. Min Act: -0.0000

Data Index: 987248 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.4375. Min Act: -0.0000

Data Index: 416691 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.4267. Min Act: -0.0000

Data Index: 923499 (C4 (Web Text))

Max Activating Token Index: 893

Text #19

Max Range: 4.6862. Min Range: -4.6862

Max Act: 3.4279. Min Act: -0.0000

Data Index: 1056182 (C4 (Web Text))

Max Activating Token Index: 963