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

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

Neuron 2977 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.7769. Min Act: -0.0000

Data Index: 577476 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.4167. Min Act: -0.0000

Data Index: 1201499 (C4 (Web Text))

Max Activating Token Index: 711

Text #2

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.2050. Min Act: -0.0000

Data Index: 396134 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.3928. Min Act: -0.0000

Data Index: 1118270 (C4 (Web Text))

Max Activating Token Index: 892

Text #4

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.3504. Min Act: -0.0000

Data Index: 1355871 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.2960. Min Act: -0.0000

Data Index: 1090504 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.0458. Min Act: -0.0000

Data Index: 833704 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.1486. Min Act: -0.0000

Data Index: 1150977 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.2149. Min Act: -0.0000

Data Index: 68173 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.1710. Min Act: -0.0000

Data Index: 1181161 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 3.7769. Min Range: -3.7769

Max Act: 3.2316. Min Act: -0.0000

Data Index: 308538 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.7027. Min Act: -0.0000

Data Index: 430037 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.8193. Min Act: -0.0000

Data Index: 507667 (C4 (Web Text))

Max Activating Token Index: 1020

Text #13

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.6993. Min Act: -0.0000

Data Index: 377553 (C4 (Web Text))

Max Activating Token Index: 590

Text #14

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.3645. Min Act: -0.0000

Data Index: 999530 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.3561. Min Act: -0.0000

Data Index: 1340431 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.2642. Min Act: -0.0000

Data Index: 103256 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.1845. Min Act: -0.0000

Data Index: 772309 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.2204. Min Act: 0.0000

Data Index: 849100 (C4 (Web Text))

Max Activating Token Index: 536

Text #19

Max Range: 3.7769. Min Range: -3.7769

Max Act: 2.3405. Min Act: -0.0000

Data Index: 527256 (C4 (Web Text))

Max Activating Token Index: 553