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

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

Neuron 1284 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.4254. Min Act: -0.0000

Data Index: 722579 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3102. Min Act: -0.0000

Data Index: 671416 (C4 (Web Text))

Max Activating Token Index: 722

Text #2

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2976. Min Act: -0.0000

Data Index: 614512 (C4 (Web Text))

Max Activating Token Index: 344

Text #3

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2982. Min Act: -0.0000

Data Index: 4406 (C4 (Web Text))

Max Activating Token Index: 94

Text #4

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2991. Min Act: -0.0000

Data Index: 543159 (C4 (Web Text))

Max Activating Token Index: 586

Text #5

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.3143. Min Act: -0.0000

Data Index: 118582 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2819. Min Act: -0.0000

Data Index: 639442 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2702. Min Act: -0.0000

Data Index: 825349 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2751. Min Act: -0.0000

Data Index: 748744 (C4 (Web Text))

Max Activating Token Index: 676

Text #9

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2755. Min Act: -0.0000

Data Index: 999363 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2505. Min Act: -0.0000

Data Index: 741444 (C4 (Web Text))

Max Activating Token Index: 210

Text #11

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2677. Min Act: -0.0000

Data Index: 746124 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2649. Min Act: -0.0000

Data Index: 299684 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2624. Min Act: -0.0000

Data Index: 547829 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2329. Min Act: -0.0000

Data Index: 770939 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2582. Min Act: -0.0000

Data Index: 388116 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2521. Min Act: -0.0000

Data Index: 619067 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2479. Min Act: -0.0000

Data Index: 160165 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2539. Min Act: -0.0000

Data Index: 544605 (C4 (Web Text))

Max Activating Token Index: 462

Text #19

Max Range: 0.4254. Min Range: -0.4254

Max Act: 0.2532. Min Act: -0.0000

Data Index: 877326 (C4 (Web Text))

Max Activating Token Index: 925