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

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

Neuron 810 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: 3.5361. Min Range: -3.5361

Max Act: 3.3607. Min Act: -0.0000

Data Index: 352878 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.3333. Min Act: -0.0000

Data Index: 336808 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.5361. Min Act: -0.0000

Data Index: 473836 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.2812. Min Act: -0.0000

Data Index: 249377 (C4 (Web Text))

Max Activating Token Index: 145

Text #4

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1843. Min Act: -0.0000

Data Index: 629070 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.1855. Min Act: -0.0000

Data Index: 246768 (C4 (Web Text))

Max Activating Token Index: 534

Text #6

Max Range: 3.5361. Min Range: -3.5361

Max Act: 3.0873. Min Act: -0.0000

Data Index: 886497 (C4 (Web Text))

Max Activating Token Index: 577

Text #7

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.8736. Min Act: -0.0000

Data Index: 1343423 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.9911. Min Act: -0.0000

Data Index: 140100 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.9253. Min Act: -0.0000

Data Index: 1379648 (Python Code)

Max Activating Token Index: 956

Text #10

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.8796. Min Act: -0.0000

Data Index: 700523 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.8575. Min Act: -0.0000

Data Index: 1003834 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.9698. Min Act: -0.0000

Data Index: 177917 (C4 (Web Text))

Max Activating Token Index: 554

Text #13

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.8232. Min Act: -0.0000

Data Index: 1218893 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.8076. Min Act: -0.0000

Data Index: 934520 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.7995. Min Act: -0.0000

Data Index: 717477 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.6565. Min Act: -0.0000

Data Index: 949897 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.7799. Min Act: -0.0000

Data Index: 689991 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.7785. Min Act: -0.0000

Data Index: 39705 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 3.5361. Min Range: -3.5361

Max Act: 2.7246. Min Act: -0.0000

Data Index: 415526 (C4 (Web Text))

Max Activating Token Index: 401