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

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

Neuron 1583 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1048561 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.4013. Min Act: -0.0000

Data Index: 647611 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.4209. Min Act: -0.0000

Data Index: 747862 (C4 (Web Text))

Max Activating Token Index: 497

Text #3

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3535. Min Act: -0.0000

Data Index: 91005 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3465. Min Act: -0.0000

Data Index: 567886 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3515. Min Act: -0.0000

Data Index: 1313158 (C4 (Web Text))

Max Activating Token Index: 242

Text #6

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1198847 (C4 (Web Text))

Max Activating Token Index: 743

Text #7

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3661. Min Act: -0.0000

Data Index: 294212 (C4 (Web Text))

Max Activating Token Index: 826

Text #8

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3423. Min Act: -0.0000

Data Index: 1161377 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3609. Min Act: -0.0000

Data Index: 252642 (C4 (Web Text))

Max Activating Token Index: 478

Text #10

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3687. Min Act: -0.0000

Data Index: 934281 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3665. Min Act: -0.0000

Data Index: 260627 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3840. Min Act: -0.0000

Data Index: 158410 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1157246 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3355. Min Act: -0.0000

Data Index: 920574 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3663. Min Act: -0.0000

Data Index: 572529 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3143. Min Act: -0.0000

Data Index: 660462 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3363. Min Act: -0.0000

Data Index: 77667 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3305. Min Act: -0.0000

Data Index: 792524 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 0.4547. Min Range: -0.4547

Max Act: 0.3216. Min Act: -0.0000

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 273