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

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

Neuron 4223 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: 2.0798. Min Range: -2.0798

Max Act: 2.0798. Min Act: -0.0000

Data Index: 888503 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.9180. Min Act: -0.0000

Data Index: 242038 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.9773. Min Act: -0.0000

Data Index: 316878 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.9459. Min Act: -0.0000

Data Index: 859345 (C4 (Web Text))

Max Activating Token Index: 305

Text #4

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.7392. Min Act: -0.0000

Data Index: 151675 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.9360. Min Act: -0.0000

Data Index: 942572 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.8843. Min Act: -0.0000

Data Index: 434117 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.8014. Min Act: -0.0000

Data Index: 1062504 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.8391. Min Act: -0.0000

Data Index: 464456 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.8657. Min Act: -0.0000

Data Index: 664545 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.8429. Min Act: -0.0000

Data Index: 218163 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.7410. Min Act: -0.0000

Data Index: 151244 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.7673. Min Act: -0.0000

Data Index: 341264 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.7774. Min Act: -0.0000

Data Index: 588255 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.6568. Min Act: -0.0000

Data Index: 792356 (C4 (Web Text))

Max Activating Token Index: 196

Text #15

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.7965. Min Act: -0.0000

Data Index: 828190 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.6906. Min Act: -0.0000

Data Index: 1198301 (C4 (Web Text))

Max Activating Token Index: 443

Text #17

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.5852. Min Act: -0.0000

Data Index: 119955 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.6280. Min Act: -0.0000

Data Index: 795652 (C4 (Web Text))

Max Activating Token Index: 950

Text #19

Max Range: 2.0798. Min Range: -2.0798

Max Act: 1.4406. Min Act: -0.0000

Data Index: 766202 (C4 (Web Text))

Max Activating Token Index: 890