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

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

Neuron 2815 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.9620. Min Act: -0.0000

Data Index: 89235 (C4 (Web Text))

Max Activating Token Index: 632

Text #1

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.6811. Min Act: -0.0000

Data Index: 1334393 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.3980. Min Act: -0.0000

Data Index: 376812 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.3872. Min Act: -0.0000

Data Index: 735929 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.2566. Min Act: -0.0000

Data Index: 548673 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.3708. Min Act: -0.0000

Data Index: 128584 (C4 (Web Text))

Max Activating Token Index: 302

Text #6

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.3277. Min Act: -0.0000

Data Index: 109458 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.2358. Min Act: -0.0000

Data Index: 332775 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.2328. Min Act: -0.0000

Data Index: 463319 (C4 (Web Text))

Max Activating Token Index: 808

Text #9

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.1923. Min Act: -0.0000

Data Index: 1012490 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.0289. Min Act: -0.0000

Data Index: 892593 (C4 (Web Text))

Max Activating Token Index: 946

Text #11

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.1609. Min Act: -0.0000

Data Index: 1201881 (C4 (Web Text))

Max Activating Token Index: 447

Text #12

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.1647. Min Act: -0.0000

Data Index: 417664 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.1549. Min Act: -0.0000

Data Index: 1357667 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.0582. Min Act: -0.0000

Data Index: 65521 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.0714. Min Act: -0.0000

Data Index: 932764 (C4 (Web Text))

Max Activating Token Index: 534

Text #16

Max Range: 2.9620. Min Range: -2.9620

Max Act: 1.9549. Min Act: -0.0000

Data Index: 957539 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 2.9620. Min Range: -2.9620

Max Act: 1.9506. Min Act: -0.0000

Data Index: 549629 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 2.9620. Min Range: -2.9620

Max Act: 1.9410. Min Act: -0.0000

Data Index: 12033 (C4 (Web Text))

Max Activating Token Index: 79

Text #19

Max Range: 2.9620. Min Range: -2.9620

Max Act: 2.0399. Min Act: -0.0000

Data Index: 942023 (C4 (Web Text))

Max Activating Token Index: 652