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

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

Neuron 2893 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0740. Min Act: -0.0002

Data Index: 285716 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0654. Min Act: -0.0002

Data Index: 254390 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0603. Min Act: -0.0002

Data Index: 593507 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0615. Min Act: -0.0002

Data Index: 964755 (C4 (Web Text))

Max Activating Token Index: 168

Text #4

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0584. Min Act: -0.0002

Data Index: 588493 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0570. Min Act: -0.0002

Data Index: 635305 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0571. Min Act: -0.0002

Data Index: 260923 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0570. Min Act: -0.0002

Data Index: 552088 (C4 (Web Text))

Max Activating Token Index: 721

Text #8

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0567. Min Act: -0.0002

Data Index: 528605 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0578. Min Act: -0.0002

Data Index: 302822 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0567. Min Act: -0.0002

Data Index: 314816 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1299782 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0551. Min Act: -0.0002

Data Index: 9316 (C4 (Web Text))

Max Activating Token Index: 89

Text #13

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0555. Min Act: -0.0002

Data Index: 111938 (C4 (Web Text))

Max Activating Token Index: 363

Text #14

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0556. Min Act: -0.0002

Data Index: 818848 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0542. Min Act: -0.0002

Data Index: 53897 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0556. Min Act: -0.0002

Data Index: 53865 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0553. Min Act: -0.0002

Data Index: 543327 (C4 (Web Text))

Max Activating Token Index: 967

Text #18

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0544. Min Act: -0.0002

Data Index: 945793 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.0740. Min Range: -0.0740

Max Act: 0.0550. Min Act: -0.0002

Data Index: 345297 (C4 (Web Text))

Max Activating Token Index: 223