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

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

Neuron 4848 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4236. Min Range: -2.4236

Max Act: 2.4236. Min Act: -0.0000

Data Index: 331109 (C4 (Web Text))

Max Activating Token Index: 274

Text #1

Max Range: 2.4236. Min Range: -2.4236

Max Act: 2.3207. Min Act: -0.0000

Data Index: 967665 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 2.4236. Min Range: -2.4236

Max Act: 2.1839. Min Act: -0.0000

Data Index: 1551857 (Python Code)

Max Activating Token Index: 148

Text #3

Max Range: 2.4236. Min Range: -2.4236

Max Act: 2.1781. Min Act: -0.0000

Data Index: 441553 (C4 (Web Text))

Max Activating Token Index: 997

Text #4

Max Range: 2.4236. Min Range: -2.4236

Max Act: 2.3055. Min Act: -0.0000

Data Index: 89068 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 2.4236. Min Range: -2.4236

Max Act: 2.0855. Min Act: -0.0000

Data Index: 1608883 (Python Code)

Max Activating Token Index: 733

Text #6

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.9321. Min Act: -0.0000

Data Index: 1420819 (Python Code)

Max Activating Token Index: 408

Text #7

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.9770. Min Act: -0.0000

Data Index: 1416733 (Python Code)

Max Activating Token Index: 587

Text #8

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.9753. Min Act: -0.0000

Data Index: 127745 (C4 (Web Text))

Max Activating Token Index: 113

Text #9

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.9623. Min Act: -0.0000

Data Index: 817036 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.9255. Min Act: -0.0000

Data Index: 1473003 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 2.4236. Min Range: -2.4236

Max Act: 2.0018. Min Act: -0.0000

Data Index: 1594366 (Python Code)

Max Activating Token Index: 89

Text #12

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.7725. Min Act: -0.0000

Data Index: 276370 (C4 (Web Text))

Max Activating Token Index: 209

Text #13

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.9467. Min Act: -0.0000

Data Index: 877818 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.8124. Min Act: -0.0000

Data Index: 272057 (C4 (Web Text))

Max Activating Token Index: 603

Text #15

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.8021. Min Act: -0.0000

Data Index: 1411924 (Python Code)

Max Activating Token Index: 752

Text #16

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.7758. Min Act: -0.0000

Data Index: 1044260 (C4 (Web Text))

Max Activating Token Index: 237

Text #17

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.7313. Min Act: -0.0000

Data Index: 87056 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.3858. Min Act: -0.0000

Data Index: 850374 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 2.4236. Min Range: -2.4236

Max Act: 1.6636. Min Act: -0.0000

Data Index: 115448 (C4 (Web Text))

Max Activating Token Index: 878