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

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

Neuron 525 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7853. Min Act: -0.0000

Data Index: 205753 (C4 (Web Text))

Max Activating Token Index: 192

Text #1

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.7143. Min Act: -0.0000

Data Index: 251522 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.6329. Min Act: -0.0000

Data Index: 1293721 (C4 (Web Text))

Max Activating Token Index: 415

Text #3

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5794. Min Act: -0.0000

Data Index: 146928 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5803. Min Act: -0.0000

Data Index: 1353076 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5757. Min Act: -0.0000

Data Index: 729236 (C4 (Web Text))

Max Activating Token Index: 1015

Text #6

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5471. Min Act: -0.0000

Data Index: 60399 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5796. Min Act: -0.0000

Data Index: 320132 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5390. Min Act: -0.0000

Data Index: 811478 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5662. Min Act: -0.0000

Data Index: 970386 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5302. Min Act: -0.0000

Data Index: 512068 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5219. Min Act: -0.0000

Data Index: 718371 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5176. Min Act: -0.0000

Data Index: 252157 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5333. Min Act: -0.0000

Data Index: 997948 (C4 (Web Text))

Max Activating Token Index: 188

Text #14

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4882. Min Act: -0.0000

Data Index: 659904 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4959. Min Act: -0.0000

Data Index: 353743 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4825. Min Act: -0.0000

Data Index: 167393 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.5153. Min Act: -0.0000

Data Index: 1330693 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4975. Min Act: -0.0000

Data Index: 671561 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.7853. Min Range: -0.7853

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1142650 (C4 (Web Text))

Max Activating Token Index: 255