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

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

Neuron 454 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: 4.4324. Min Range: -4.4324

Max Act: 4.2413. Min Act: -0.0001

Data Index: 931483 (C4 (Web Text))

Max Activating Token Index: 818

Text #1

Max Range: 4.4324. Min Range: -4.4324

Max Act: 4.0014. Min Act: -0.0001

Data Index: 665532 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 4.4324. Min Range: -4.4324

Max Act: 4.4324. Min Act: -0.0000

Data Index: 1151622 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.9426. Min Act: -0.0000

Data Index: 770353 (C4 (Web Text))

Max Activating Token Index: 576

Text #4

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.9619. Min Act: -0.0001

Data Index: 486733 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 4.4324. Min Range: -4.4324

Max Act: 4.2007. Min Act: -0.0001

Data Index: 721106 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 4.4324. Min Range: -4.4324

Max Act: 4.1668. Min Act: -0.0001

Data Index: 707379 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.9692. Min Act: -0.0000

Data Index: 404973 (C4 (Web Text))

Max Activating Token Index: 627

Text #8

Max Range: 4.4324. Min Range: -4.4324

Max Act: 4.1081. Min Act: -0.0001

Data Index: 1035705 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 4.4324. Min Range: -4.4324

Max Act: 4.0861. Min Act: -0.0000

Data Index: 1056034 (C4 (Web Text))

Max Activating Token Index: 754

Text #10

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.5564. Min Act: -0.0000

Data Index: 722455 (C4 (Web Text))

Max Activating Token Index: 181

Text #11

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.5614. Min Act: -0.0001

Data Index: 477472 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.8613. Min Act: -0.0001

Data Index: 423003 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.6955. Min Act: -0.0000

Data Index: 1083578 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.5484. Min Act: -0.0001

Data Index: 876795 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.6984. Min Act: -0.0001

Data Index: 364663 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.6721. Min Act: -0.0001

Data Index: 275109 (C4 (Web Text))

Max Activating Token Index: 781

Text #17

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.6634. Min Act: -0.0001

Data Index: 936201 (C4 (Web Text))

Max Activating Token Index: 76

Text #18

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.3459. Min Act: -0.0001

Data Index: 185264 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 4.4324. Min Range: -4.4324

Max Act: 3.1349. Min Act: -0.0000

Data Index: 714362 (C4 (Web Text))

Max Activating Token Index: 375