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

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

Neuron 4864 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1376. Min Range: -2.1376

Max Act: 2.1376. Min Act: -0.0000

Data Index: 701233 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 2.1376. Min Range: -2.1376

Max Act: 2.0258. Min Act: -0.0000

Data Index: 783499 (C4 (Web Text))

Max Activating Token Index: 506

Text #2

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.7395. Min Act: -0.0000

Data Index: 301389 (C4 (Web Text))

Max Activating Token Index: 474

Text #3

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.5697. Min Act: -0.0000

Data Index: 1137522 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.5576. Min Act: -0.0000

Data Index: 70467 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2985. Min Act: -0.0000

Data Index: 816406 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2807. Min Act: -0.0000

Data Index: 126710 (C4 (Web Text))

Max Activating Token Index: 726

Text #7

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2712. Min Act: -0.0000

Data Index: 526133 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2943. Min Act: -0.0000

Data Index: 602639 (C4 (Web Text))

Max Activating Token Index: 515

Text #9

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1269277 (C4 (Web Text))

Max Activating Token Index: 678

Text #10

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2918. Min Act: -0.0000

Data Index: 1171627 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2395. Min Act: -0.0000

Data Index: 54899 (C4 (Web Text))

Max Activating Token Index: 407

Text #12

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.1712. Min Act: -0.0001

Data Index: 476482 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.2450. Min Act: -0.0000

Data Index: 724118 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.1156. Min Act: -0.0000

Data Index: 1171366 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.1695. Min Act: -0.0000

Data Index: 1273376 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.1711. Min Act: -0.0000

Data Index: 1181501 (C4 (Web Text))

Max Activating Token Index: 494

Text #17

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.1226. Min Act: -0.0000

Data Index: 961989 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.1690. Min Act: -0.0000

Data Index: 755650 (C4 (Web Text))

Max Activating Token Index: 570

Text #19

Max Range: 2.1376. Min Range: -2.1376

Max Act: 1.0929. Min Act: -0.0000

Data Index: 473595 (C4 (Web Text))

Max Activating Token Index: 664