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

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

Neuron 5392 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.8598. Min Act: -0.0000

Data Index: 32003 (C4 (Web Text))

Max Activating Token Index: 568

Text #1

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7863. Min Act: -0.0000

Data Index: 44498 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.8344. Min Act: -0.0000

Data Index: 53534 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7801. Min Act: -0.0000

Data Index: 553909 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1149101 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7016. Min Act: -0.0000

Data Index: 345461 (C4 (Web Text))

Max Activating Token Index: 414

Text #6

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7282. Min Act: -0.0000

Data Index: 40437 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6626. Min Act: -0.0000

Data Index: 1095949 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7482. Min Act: -0.0000

Data Index: 684119 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7023. Min Act: -0.0000

Data Index: 174415 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6655. Min Act: -0.0000

Data Index: 1152701 (C4 (Web Text))

Max Activating Token Index: 850

Text #11

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6491. Min Act: -0.0000

Data Index: 10473 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6834. Min Act: -0.0000

Data Index: 311934 (C4 (Web Text))

Max Activating Token Index: 676

Text #13

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6620. Min Act: -0.0000

Data Index: 18523 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7279. Min Act: -0.0000

Data Index: 1490741 (Python Code)

Max Activating Token Index: 868

Text #15

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7514. Min Act: -0.0000

Data Index: 129978 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.7251. Min Act: -0.0000

Data Index: 624637 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6658. Min Act: -0.0000

Data Index: 900091 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6977. Min Act: -0.0000

Data Index: 856202 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 0.8598. Min Range: -0.8598

Max Act: 0.6194. Min Act: -0.0000

Data Index: 752010 (C4 (Web Text))

Max Activating Token Index: 108