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

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

Neuron 1858 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0002

Data Index: 661405 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1078945 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0717. Min Act: -0.0002

Data Index: 683451 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0705. Min Act: -0.0002

Data Index: 377447 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0700. Min Act: -0.0002

Data Index: 134332 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0701. Min Act: -0.0002

Data Index: 78057 (C4 (Web Text))

Max Activating Token Index: 615

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0669. Min Act: -0.0002

Data Index: 584805 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1091765 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0668. Min Act: -0.0002

Data Index: 442981 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0696. Min Act: -0.0002

Data Index: 910388 (C4 (Web Text))

Max Activating Token Index: 229

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1187917 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0662. Min Act: -0.0002

Data Index: 1254846 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0653. Min Act: -0.0002

Data Index: 375461 (C4 (Web Text))

Max Activating Token Index: 653

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0629. Min Act: -0.0002

Data Index: 697528 (C4 (Web Text))

Max Activating Token Index: 763

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0615. Min Act: -0.0002

Data Index: 638667 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0619. Min Act: -0.0002

Data Index: 6318 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0593. Min Act: -0.0002

Data Index: 890066 (C4 (Web Text))

Max Activating Token Index: 782

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0586. Min Act: -0.0002

Data Index: 229223 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0585. Min Act: -0.0002

Data Index: 47068 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1245405 (C4 (Web Text))

Max Activating Token Index: 553