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

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

Neuron 3129 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: 1.5981. Min Range: -1.5981

Max Act: 1.5551. Min Act: -0.0000

Data Index: 1543218 (Python Code)

Max Activating Token Index: 113

Text #1

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.5981. Min Act: -0.0000

Data Index: 66631 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3511. Min Act: -0.0000

Data Index: 160991 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.3213. Min Act: -0.0000

Data Index: 1541647 (Python Code)

Max Activating Token Index: 31

Text #4

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1541905 (Python Code)

Max Activating Token Index: 102

Text #5

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2463. Min Act: -0.0000

Data Index: 1486801 (Python Code)

Max Activating Token Index: 658

Text #6

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2515. Min Act: -0.0000

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2330. Min Act: -0.0000

Data Index: 1401821 (Python Code)

Max Activating Token Index: 171

Text #8

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2703. Min Act: -0.0000

Data Index: 1470368 (Python Code)

Max Activating Token Index: 143

Text #9

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2803. Min Act: -0.0000

Data Index: 1653396 (Python Code)

Max Activating Token Index: 588

Text #10

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2328. Min Act: -0.0000

Data Index: 1601292 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.1614. Min Act: -0.0000

Data Index: 1652661 (Python Code)

Max Activating Token Index: 643

Text #12

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.0347. Min Act: -0.0000

Data Index: 993146 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2090. Min Act: -0.0000

Data Index: 512972 (C4 (Web Text))

Max Activating Token Index: 17

Text #14

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.1640. Min Act: -0.0000

Data Index: 1605622 (Python Code)

Max Activating Token Index: 15

Text #15

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2096. Min Act: -0.0000

Data Index: 1456088 (Python Code)

Max Activating Token Index: 154

Text #16

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.2495. Min Act: -0.0000

Data Index: 14579 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.1539. Min Act: -0.0000

Data Index: 1610288 (Python Code)

Max Activating Token Index: 146

Text #18

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.1873. Min Act: -0.0000

Data Index: 1180187 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.5981. Min Range: -1.5981

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1573329 (Python Code)

Max Activating Token Index: 588