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

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

Neuron 1605 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: 3.0452. Min Range: -3.0452

Max Act: 3.0394. Min Act: -0.0000

Data Index: 547303 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 3.0452. Min Range: -3.0452

Max Act: 3.0304. Min Act: -0.0000

Data Index: 1038244 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.8409. Min Act: -0.0000

Data Index: 1026335 (C4 (Web Text))

Max Activating Token Index: 904

Text #3

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.7891. Min Act: -0.0000

Data Index: 820383 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.6179. Min Act: -0.0000

Data Index: 878363 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.7679. Min Act: -0.0000

Data Index: 402162 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.5165. Min Act: -0.0000

Data Index: 1226081 (C4 (Web Text))

Max Activating Token Index: 239

Text #7

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.9317. Min Act: -0.0000

Data Index: 629087 (C4 (Web Text))

Max Activating Token Index: 260

Text #8

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.9035. Min Act: -0.0000

Data Index: 255996 (C4 (Web Text))

Max Activating Token Index: 889

Text #9

Max Range: 3.0452. Min Range: -3.0452

Max Act: 3.0452. Min Act: -0.0000

Data Index: 1546990 (Python Code)

Max Activating Token Index: 423

Text #10

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.5697. Min Act: -0.0000

Data Index: 602770 (C4 (Web Text))

Max Activating Token Index: 285

Text #11

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.4198. Min Act: -0.0000

Data Index: 952563 (C4 (Web Text))

Max Activating Token Index: 259

Text #12

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.4589. Min Act: -0.0000

Data Index: 755378 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.4394. Min Act: -0.0000

Data Index: 5853 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.5304. Min Act: -0.0000

Data Index: 1017859 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.4317. Min Act: -0.0000

Data Index: 812725 (C4 (Web Text))

Max Activating Token Index: 486

Text #16

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.5185. Min Act: -0.0000

Data Index: 1231365 (C4 (Web Text))

Max Activating Token Index: 216

Text #17

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.4955. Min Act: -0.0000

Data Index: 496457 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.6513. Min Act: -0.0000

Data Index: 962073 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 3.0452. Min Range: -3.0452

Max Act: 2.1431. Min Act: -0.0000

Data Index: 497555 (C4 (Web Text))

Max Activating Token Index: 654