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

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

Neuron 428 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: 4.0248. Min Range: -4.0248

Max Act: 3.8928. Min Act: -0.0000

Data Index: 994190 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 4.0248. Min Range: -4.0248

Max Act: 4.0248. Min Act: -0.0000

Data Index: 1105914 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.9677. Min Act: -0.0000

Data Index: 218543 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.6925. Min Act: -0.0000

Data Index: 4555 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 4.0248. Min Range: -4.0248

Max Act: 4.0067. Min Act: -0.0000

Data Index: 606986 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.5996. Min Act: -0.0000

Data Index: 1238679 (C4 (Web Text))

Max Activating Token Index: 730

Text #6

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.5525. Min Act: -0.0000

Data Index: 226609 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.5653. Min Act: -0.0000

Data Index: 77935 (C4 (Web Text))

Max Activating Token Index: 17

Text #8

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.4709. Min Act: -0.0000

Data Index: 895923 (C4 (Web Text))

Max Activating Token Index: 484

Text #9

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.5995. Min Act: -0.0000

Data Index: 984892 (C4 (Web Text))

Max Activating Token Index: 257

Text #10

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.3707. Min Act: -0.0000

Data Index: 917489 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.3376. Min Act: -0.0000

Data Index: 442305 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.3453. Min Act: -0.0000

Data Index: 922851 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.1778. Min Act: -0.0000

Data Index: 140830 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.3913. Min Act: -0.0000

Data Index: 975394 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.4948. Min Act: -0.0000

Data Index: 129499 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.1631. Min Act: -0.0000

Data Index: 603958 (C4 (Web Text))

Max Activating Token Index: 521

Text #17

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.1283. Min Act: -0.0000

Data Index: 178123 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.3946. Min Act: -0.0000

Data Index: 625099 (C4 (Web Text))

Max Activating Token Index: 449

Text #19

Max Range: 4.0248. Min Range: -4.0248

Max Act: 3.2329. Min Act: -0.0000

Data Index: 486904 (C4 (Web Text))

Max Activating Token Index: 340