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

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

Neuron 1858 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: 1.4712. Min Range: -1.4712

Max Act: 1.4712. Min Act: -0.0000

Data Index: 288578 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.4121. Min Act: -0.0000

Data Index: 932514 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.4584. Min Act: -0.0000

Data Index: 889229 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3800. Min Act: -0.0000

Data Index: 185158 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3992. Min Act: -0.0000

Data Index: 704729 (C4 (Web Text))

Max Activating Token Index: 382

Text #5

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3271. Min Act: -0.0000

Data Index: 327305 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.4315. Min Act: -0.0000

Data Index: 215543 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.4092. Min Act: -0.0000

Data Index: 234063 (C4 (Web Text))

Max Activating Token Index: 445

Text #8

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3790. Min Act: -0.0000

Data Index: 311665 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3810. Min Act: -0.0000

Data Index: 307618 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3349. Min Act: -0.0000

Data Index: 442235 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3651. Min Act: -0.0000

Data Index: 672390 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2365. Min Act: -0.0000

Data Index: 870204 (C4 (Web Text))

Max Activating Token Index: 382

Text #13

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3527. Min Act: -0.0000

Data Index: 545535 (C4 (Web Text))

Max Activating Token Index: 673

Text #14

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2671. Min Act: -0.0000

Data Index: 198215 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.3275. Min Act: -0.0000

Data Index: 177862 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2808. Min Act: -0.0000

Data Index: 811334 (C4 (Web Text))

Max Activating Token Index: 522

Text #17

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2752. Min Act: -0.0000

Data Index: 654993 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.2430. Min Act: -0.0000

Data Index: 490286 (C4 (Web Text))

Max Activating Token Index: 842

Text #19

Max Range: 1.4712. Min Range: -1.4712

Max Act: 1.1976. Min Act: -0.0000

Data Index: 390505 (C4 (Web Text))

Max Activating Token Index: 289