Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1904 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 5.3826. Min Range: -5.3826

Max Act: 5.3826. Min Act: -0.0000

Data Index: 1261435 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.9795. Min Act: -0.0000

Data Index: 315007 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.5771. Min Act: -0.0000

Data Index: 787060 (C4 (Web Text))

Max Activating Token Index: 171

Text #3

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.5752. Min Act: -0.0000

Data Index: 761335 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.5702. Min Act: -0.0000

Data Index: 1150644 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.4183. Min Act: -0.0000

Data Index: 154933 (C4 (Web Text))

Max Activating Token Index: 396

Text #6

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.3274. Min Act: -0.0000

Data Index: 1044040 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.2801. Min Act: -0.0000

Data Index: 1334458 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.0756. Min Act: -0.0000

Data Index: 1352588 (C4 (Web Text))

Max Activating Token Index: 55

Text #9

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.1774. Min Act: -0.0000

Data Index: 1029343 (C4 (Web Text))

Max Activating Token Index: 734

Text #10

Max Range: 5.3826. Min Range: -5.3826

Max Act: 3.9552. Min Act: -0.0000

Data Index: 589198 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.0918. Min Act: -0.0000

Data Index: 1276527 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 5.3826. Min Range: -5.3826

Max Act: 3.9791. Min Act: -0.0000

Data Index: 981559 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.1369. Min Act: -0.0000

Data Index: 392876 (C4 (Web Text))

Max Activating Token Index: 766

Text #14

Max Range: 5.3826. Min Range: -5.3826

Max Act: 4.0772. Min Act: -0.0000

Data Index: 109628 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 5.3826. Min Range: -5.3826

Max Act: 3.6369. Min Act: -0.0000

Data Index: 1206915 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 5.3826. Min Range: -5.3826

Max Act: 3.7887. Min Act: -0.0000

Data Index: 104427 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 5.3826. Min Range: -5.3826

Max Act: 3.5404. Min Act: -0.0000

Data Index: 230531 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 5.3826. Min Range: -5.3826

Max Act: 3.4513. Min Act: -0.0000

Data Index: 355469 (C4 (Web Text))

Max Activating Token Index: 307

Text #19

Max Range: 5.3826. Min Range: -5.3826

Max Act: 3.4165. Min Act: -0.0000

Data Index: 208433 (C4 (Web Text))

Max Activating Token Index: 669