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

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

Neuron 2823 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.5281. Min Act: -0.0000

Data Index: 951075 (C4 (Web Text))

Max Activating Token Index: 316

Text #1

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.4864. Min Act: -0.0000

Data Index: 749955 (C4 (Web Text))

Max Activating Token Index: 660

Text #2

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.4627. Min Act: -0.0000

Data Index: 795787 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.4340. Min Act: -0.0000

Data Index: 1135896 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.4549. Min Act: -0.0000

Data Index: 344930 (C4 (Web Text))

Max Activating Token Index: 299

Text #5

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.4219. Min Act: -0.0000

Data Index: 443557 (C4 (Web Text))

Max Activating Token Index: 529

Text #6

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.4001. Min Act: -0.0000

Data Index: 419021 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3818. Min Act: -0.0000

Data Index: 15566 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3798. Min Act: -0.0000

Data Index: 941204 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3655. Min Act: -0.0000

Data Index: 648335 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3618. Min Act: -0.0000

Data Index: 1010306 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3484. Min Act: -0.0000

Data Index: 507878 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3460. Min Act: -0.0000

Data Index: 7043 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3544. Min Act: -0.0000

Data Index: 289107 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1291917 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3161. Min Act: -0.0000

Data Index: 1182971 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3042. Min Act: -0.0000

Data Index: 498483 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.2910. Min Act: -0.0000

Data Index: 124708 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.2963. Min Act: -0.0000

Data Index: 1343890 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.5281. Min Range: -0.5281

Max Act: 0.3162. Min Act: -0.0000

Data Index: 1012581 (C4 (Web Text))

Max Activating Token Index: 934