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

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

Neuron 2496 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: 1.5870. Min Range: -1.5870

Max Act: 1.5870. Min Act: -0.0000

Data Index: 747697 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4471. Min Act: -0.0000

Data Index: 665519 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3668. Min Act: -0.0000

Data Index: 554652 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4432. Min Act: -0.0000

Data Index: 1349704 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4627. Min Act: -0.0000

Data Index: 437972 (C4 (Web Text))

Max Activating Token Index: 272

Text #5

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4468. Min Act: -0.0000

Data Index: 265281 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4121. Min Act: -0.0000

Data Index: 255154 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4048. Min Act: -0.0000

Data Index: 1013517 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4112. Min Act: -0.0000

Data Index: 922922 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3753. Min Act: -0.0000

Data Index: 952870 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3591. Min Act: -0.0000

Data Index: 233756 (C4 (Web Text))

Max Activating Token Index: 332

Text #11

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3335. Min Act: -0.0000

Data Index: 92503 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.4099. Min Act: -0.0000

Data Index: 256393 (C4 (Web Text))

Max Activating Token Index: 903

Text #13

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.2127. Min Act: -0.0000

Data Index: 161936 (C4 (Web Text))

Max Activating Token Index: 39

Text #14

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3477. Min Act: -0.0000

Data Index: 140689 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.1921. Min Act: -0.0000

Data Index: 1312042 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.3327. Min Act: -0.0000

Data Index: 224396 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.2370. Min Act: -0.0000

Data Index: 790665 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.2372. Min Act: -0.0000

Data Index: 1135716 (C4 (Web Text))

Max Activating Token Index: 283

Text #19

Max Range: 1.5870. Min Range: -1.5870

Max Act: 1.2339. Min Act: -0.0000

Data Index: 363505 (C4 (Web Text))

Max Activating Token Index: 375