Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4654 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0730. Min Act: -0.0002

Data Index: 764001 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0664. Min Act: -0.0002

Data Index: 197360 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0601. Min Act: -0.0002

Data Index: 832822 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0555. Min Act: -0.0002

Data Index: 634819 (C4 (Web Text))

Max Activating Token Index: 421

Text #4

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0571. Min Act: -0.0002

Data Index: 331373 (C4 (Web Text))

Max Activating Token Index: 385

Text #5

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0563. Min Act: -0.0003

Data Index: 252066 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0557. Min Act: -0.0002

Data Index: 1336830 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0592. Min Act: -0.0002

Data Index: 339704 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0524. Min Act: -0.0002

Data Index: 142993 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0540. Min Act: -0.0002

Data Index: 518409 (C4 (Web Text))

Max Activating Token Index: 497

Text #10

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0553. Min Act: -0.0002

Data Index: 1196299 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0539. Min Act: -0.0002

Data Index: 647794 (C4 (Web Text))

Max Activating Token Index: 560

Text #12

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0539. Min Act: -0.0002

Data Index: 240819 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0470. Min Act: -0.0002

Data Index: 960989 (C4 (Web Text))

Max Activating Token Index: 197

Text #14

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0572. Min Act: -0.0002

Data Index: 224355 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0501. Min Act: -0.0002

Data Index: 227723 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1350503 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0489. Min Act: -0.0002

Data Index: 614628 (C4 (Web Text))

Max Activating Token Index: 885

Text #18

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0489. Min Act: -0.0002

Data Index: 155279 (C4 (Web Text))

Max Activating Token Index: 580

Text #19

Max Range: 0.0730. Min Range: -0.0730

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1319740 (C4 (Web Text))

Max Activating Token Index: 429