Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4537 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.8895. Min Act: -0.0000

Data Index: 1107217 (C4 (Web Text))

Max Activating Token Index: 47

Text #1

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.9563. Min Act: -0.0000

Data Index: 856830 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6606. Min Act: -0.0000

Data Index: 196698 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.7162. Min Act: -0.0000

Data Index: 1050285 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6151. Min Act: -0.0000

Data Index: 338709 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.5950. Min Act: -0.0000

Data Index: 450857 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.6847. Min Act: -0.0000

Data Index: 1132491 (C4 (Web Text))

Max Activating Token Index: 7

Text #7

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.5354. Min Act: -0.0000

Data Index: 1169197 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.4537. Min Act: -0.0000

Data Index: 243131 (C4 (Web Text))

Max Activating Token Index: 54

Text #9

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.4127. Min Act: -0.0000

Data Index: 645333 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.4032. Min Act: -0.0000

Data Index: 850260 (C4 (Web Text))

Max Activating Token Index: 338

Text #11

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.4064. Min Act: -0.0000

Data Index: 918692 (C4 (Web Text))

Max Activating Token Index: 977

Text #12

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.2817. Min Act: -0.0000

Data Index: 224510 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.4442. Min Act: -0.0000

Data Index: 400429 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.3984. Min Act: -0.0000

Data Index: 142370 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.3960. Min Act: -0.0000

Data Index: 1286287 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.2857. Min Act: -0.0000

Data Index: 1304705 (C4 (Web Text))

Max Activating Token Index: 595

Text #17

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.3708. Min Act: -0.0000

Data Index: 207208 (C4 (Web Text))

Max Activating Token Index: 542

Text #18

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.2054. Min Act: -0.0000

Data Index: 85419 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 1.9563. Min Range: -1.9563

Max Act: 1.3479. Min Act: -0.0000

Data Index: 83011 (C4 (Web Text))

Max Activating Token Index: 463