Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2037 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.2331. Min Range: -2.2331

Max Act: 2.2331. Min Act: -0.0001

Data Index: 529466 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.8479. Min Act: -0.0001

Data Index: 1125621 (C4 (Web Text))

Max Activating Token Index: 599

Text #2

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.7121. Min Act: -0.0001

Data Index: 1249514 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.4649. Min Act: -0.0000

Data Index: 696242 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.4216. Min Act: -0.0001

Data Index: 1040077 (C4 (Web Text))

Max Activating Token Index: 447

Text #5

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.4045. Min Act: -0.0001

Data Index: 156311 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.4965. Min Act: -0.0000

Data Index: 1001391 (C4 (Web Text))

Max Activating Token Index: 798

Text #7

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.3815. Min Act: -0.0001

Data Index: 677529 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.2950. Min Act: -0.0000

Data Index: 822064 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.2897. Min Act: -0.0000

Data Index: 1270755 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.4096. Min Act: -0.0000

Data Index: 204244 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.2444. Min Act: -0.0001

Data Index: 718912 (C4 (Web Text))

Max Activating Token Index: 29

Text #12

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1141803 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.1792. Min Act: -0.0001

Data Index: 215094 (C4 (Web Text))

Max Activating Token Index: 532

Text #14

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.2171. Min Act: -0.0000

Data Index: 136945 (C4 (Web Text))

Max Activating Token Index: 552

Text #15

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.3607. Min Act: -0.0001

Data Index: 863609 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.1915. Min Act: -0.0001

Data Index: 704755 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.2133. Min Act: -0.0000

Data Index: 1347242 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.1849. Min Act: -0.0000

Data Index: 21007 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 2.2331. Min Range: -2.2331

Max Act: 1.1431. Min Act: -0.0001

Data Index: 290167 (C4 (Web Text))

Max Activating Token Index: 459