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

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

Neuron 2300 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: 2.9796. Min Range: -2.9796

Max Act: 2.8240. Min Act: -0.0000

Data Index: 335379 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.9673. Min Act: -0.0000

Data Index: 920838 (C4 (Web Text))

Max Activating Token Index: 618

Text #2

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.6496. Min Act: -0.0000

Data Index: 395487 (C4 (Web Text))

Max Activating Token Index: 865

Text #3

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.9045. Min Act: -0.0000

Data Index: 550933 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.4395. Min Act: -0.0000

Data Index: 1343140 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.9796. Min Act: -0.0000

Data Index: 112046 (C4 (Web Text))

Max Activating Token Index: 315

Text #6

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.5269. Min Act: -0.0000

Data Index: 589050 (C4 (Web Text))

Max Activating Token Index: 27

Text #7

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.2542. Min Act: -0.0000

Data Index: 110507 (C4 (Web Text))

Max Activating Token Index: 26

Text #8

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.5905. Min Act: -0.0000

Data Index: 106500 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.4551. Min Act: -0.0000

Data Index: 241053 (C4 (Web Text))

Max Activating Token Index: 394

Text #10

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.3798. Min Act: -0.0000

Data Index: 1270068 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.3016. Min Act: -0.0000

Data Index: 650466 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.3751. Min Act: -0.0000

Data Index: 182833 (C4 (Web Text))

Max Activating Token Index: 943

Text #13

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.2116. Min Act: -0.0000

Data Index: 13517 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.0530. Min Act: -0.0000

Data Index: 1349156 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.1850. Min Act: -0.0000

Data Index: 1028994 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.0335. Min Act: -0.0000

Data Index: 1275233 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 2.9796. Min Range: -2.9796

Max Act: 1.9057. Min Act: -0.0000

Data Index: 362051 (C4 (Web Text))

Max Activating Token Index: 561

Text #18

Max Range: 2.9796. Min Range: -2.9796

Max Act: 2.0059. Min Act: -0.0000

Data Index: 266467 (C4 (Web Text))

Max Activating Token Index: 198

Text #19

Max Range: 2.9796. Min Range: -2.9796

Max Act: 1.9687. Min Act: -0.0000

Data Index: 694398 (C4 (Web Text))

Max Activating Token Index: 351