Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1175 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0574. Min Act: -0.0005

Data Index: 963473 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0557. Min Act: -0.0005

Data Index: 1412765 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0566. Min Act: -0.0005

Data Index: 1126116 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0516. Min Act: -0.0005

Data Index: 1416814 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0523. Min Act: -0.0005

Data Index: 1486101 (Python Code)

Max Activating Token Index: 109

Text #5

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0519. Min Act: -0.0005

Data Index: 288065 (C4 (Web Text))

Max Activating Token Index: 24

Text #6

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0505. Min Act: -0.0005

Data Index: 1633891 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0458. Min Act: -0.0005

Data Index: 505849 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0493. Min Act: -0.0005

Data Index: 414790 (C4 (Web Text))

Max Activating Token Index: 292

Text #9

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0513. Min Act: -0.0005

Data Index: 1558775 (Python Code)

Max Activating Token Index: 881

Text #10

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0473. Min Act: -0.0005

Data Index: 1140533 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0571. Min Act: -0.0005

Data Index: 994270 (C4 (Web Text))

Max Activating Token Index: 335

Text #12

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0513. Min Act: -0.0005

Data Index: 781343 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0472. Min Act: -0.0005

Data Index: 206878 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0401. Min Act: -0.0005

Data Index: 570187 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0475. Min Act: -0.0005

Data Index: 620687 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0483. Min Act: -0.0005

Data Index: 1622181 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0404. Min Act: -0.0005

Data Index: 342535 (C4 (Web Text))

Max Activating Token Index: 642

Text #18

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0463. Min Act: -0.0005

Data Index: 721088 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.0574. Min Range: -0.0574

Max Act: 0.0490. Min Act: -0.0005

Data Index: 403326 (C4 (Web Text))

Max Activating Token Index: 102