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

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

Neuron 4575 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.7720. Min Act: -0.0000

Data Index: 283239 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.8041. Min Act: -0.0000

Data Index: 691066 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6314. Min Act: -0.0000

Data Index: 719271 (C4 (Web Text))

Max Activating Token Index: 281

Text #3

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6502. Min Act: -0.0000

Data Index: 276583 (C4 (Web Text))

Max Activating Token Index: 375

Text #4

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6514. Min Act: -0.0000

Data Index: 1305379 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5996. Min Act: -0.0000

Data Index: 441003 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5716. Min Act: -0.0000

Data Index: 506688 (C4 (Web Text))

Max Activating Token Index: 899

Text #7

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.6205. Min Act: -0.0000

Data Index: 469430 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5589. Min Act: -0.0000

Data Index: 1138941 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5316. Min Act: -0.0000

Data Index: 903168 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5437. Min Act: -0.0000

Data Index: 211163 (C4 (Web Text))

Max Activating Token Index: 795

Text #11

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5434. Min Act: -0.0000

Data Index: 790762 (C4 (Web Text))

Max Activating Token Index: 155

Text #12

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5769. Min Act: -0.0000

Data Index: 49555 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5007. Min Act: -0.0000

Data Index: 163566 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5268. Min Act: -0.0000

Data Index: 515704 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1348941 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4742. Min Act: -0.0000

Data Index: 177915 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4215. Min Act: -0.0000

Data Index: 1237673 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.4894. Min Act: -0.0000

Data Index: 1280434 (C4 (Web Text))

Max Activating Token Index: 1019

Text #19

Max Range: 0.8041. Min Range: -0.8041

Max Act: 0.5182. Min Act: -0.0000

Data Index: 560560 (C4 (Web Text))

Max Activating Token Index: 288