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

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

Neuron 5196 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.1629. Min Act: -0.0000

Data Index: 690696 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.0958. Min Act: -0.0000

Data Index: 1239003 (C4 (Web Text))

Max Activating Token Index: 404

Text #2

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.2242. Min Act: -0.0000

Data Index: 417847 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.9066. Min Act: -0.0000

Data Index: 888016 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 3.2242. Min Range: -3.2242

Max Act: 3.0169. Min Act: -0.0000

Data Index: 1275489 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.8901. Min Act: -0.0000

Data Index: 324771 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.8896. Min Act: -0.0000

Data Index: 774724 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.8264. Min Act: -0.0000

Data Index: 1093774 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.5583. Min Act: -0.0000

Data Index: 411163 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.6676. Min Act: -0.0000

Data Index: 1185045 (C4 (Web Text))

Max Activating Token Index: 546

Text #10

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.5098. Min Act: -0.0000

Data Index: 976653 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.7391. Min Act: -0.0000

Data Index: 835173 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.5694. Min Act: -0.0000

Data Index: 577935 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.4142. Min Act: -0.0000

Data Index: 877532 (C4 (Web Text))

Max Activating Token Index: 701

Text #14

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.5232. Min Act: -0.0000

Data Index: 886580 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.5076. Min Act: -0.0000

Data Index: 596394 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.3355. Min Act: -0.0000

Data Index: 705498 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.4270. Min Act: -0.0000

Data Index: 1234953 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.1605. Min Act: -0.0000

Data Index: 1294339 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 3.2242. Min Range: -3.2242

Max Act: 2.2504. Min Act: -0.0000

Data Index: 334430 (C4 (Web Text))

Max Activating Token Index: 1009