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

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

Neuron 3291 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3278. Min Range: -3.3278

Max Act: 3.3278. Min Act: -0.0000

Data Index: 1024377 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 3.3278. Min Range: -3.3278

Max Act: 3.0322. Min Act: 0.0000

Data Index: 62930 (C4 (Web Text))

Max Activating Token Index: 663

Text #2

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.7012. Min Act: -0.0000

Data Index: 1303646 (C4 (Web Text))

Max Activating Token Index: 271

Text #3

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.5555. Min Act: -0.0000

Data Index: 695794 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.5144. Min Act: -0.0000

Data Index: 692160 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.6490. Min Act: -0.0000

Data Index: 429495 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.4960. Min Act: -0.0000

Data Index: 1415502 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.4833. Min Act: -0.0000

Data Index: 347162 (C4 (Web Text))

Max Activating Token Index: 427

Text #8

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.4885. Min Act: -0.0000

Data Index: 771275 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.4402. Min Act: -0.0000

Data Index: 1411413 (Python Code)

Max Activating Token Index: 174

Text #10

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.4085. Min Act: 0.0000

Data Index: 811192 (C4 (Web Text))

Max Activating Token Index: 665

Text #11

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.5064. Min Act: -0.0000

Data Index: 50842 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.3693. Min Act: -0.0000

Data Index: 896725 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.3828. Min Act: -0.0000

Data Index: 656050 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.3180. Min Act: 0.0000

Data Index: 850508 (C4 (Web Text))

Max Activating Token Index: 725

Text #15

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.1832. Min Act: -0.0000

Data Index: 1204545 (C4 (Web Text))

Max Activating Token Index: 709

Text #16

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.2574. Min Act: -0.0000

Data Index: 572998 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.2471. Min Act: -0.0000

Data Index: 173615 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.1809. Min Act: 0.0000

Data Index: 404613 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 3.3278. Min Range: -3.3278

Max Act: 2.0302. Min Act: -0.0000

Data Index: 373393 (C4 (Web Text))

Max Activating Token Index: 936