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

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

Neuron 2034 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: 0.5514. Min Range: -0.5514

Max Act: 0.5514. Min Act: 0.0000

Data Index: 1070638 (C4 (Web Text))

Max Activating Token Index: 556

Text #1

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5207. Min Act: -0.0000

Data Index: 498842 (C4 (Web Text))

Max Activating Token Index: 297

Text #2

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5355. Min Act: -0.0000

Data Index: 1071659 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5031. Min Act: 0.0000

Data Index: 226660 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5107. Min Act: -0.0000

Data Index: 725756 (C4 (Web Text))

Max Activating Token Index: 275

Text #5

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5108. Min Act: -0.0000

Data Index: 365631 (C4 (Web Text))

Max Activating Token Index: 788

Text #6

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1163424 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5329. Min Act: -0.0000

Data Index: 92477 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4820. Min Act: -0.0000

Data Index: 370622 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.5009. Min Act: -0.0000

Data Index: 458659 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4842. Min Act: 0.0000

Data Index: 183747 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4897. Min Act: -0.0000

Data Index: 830690 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4703. Min Act: -0.0000

Data Index: 2608 (C4 (Web Text))

Max Activating Token Index: 971

Text #13

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4802. Min Act: -0.0000

Data Index: 339395 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4532. Min Act: -0.0000

Data Index: 838737 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1192012 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1083684 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1330895 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4520. Min Act: 0.0000

Data Index: 476999 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.5514. Min Range: -0.5514

Max Act: 0.4343. Min Act: 0.0000

Data Index: 623344 (C4 (Web Text))

Max Activating Token Index: 536