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

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

Neuron 3562 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3867. Min Range: -2.3867

Max Act: 2.3867. Min Act: -0.0000

Data Index: 869921 (C4 (Web Text))

Max Activating Token Index: 418

Text #1

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.6661. Min Act: -0.0000

Data Index: 1041504 (C4 (Web Text))

Max Activating Token Index: 471

Text #2

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.7341. Min Act: -0.0000

Data Index: 369857 (C4 (Web Text))

Max Activating Token Index: 164

Text #3

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.5293. Min Act: -0.0000

Data Index: 871714 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.8049. Min Act: -0.0000

Data Index: 393277 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.5368. Min Act: -0.0000

Data Index: 1032889 (C4 (Web Text))

Max Activating Token Index: 553

Text #6

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.6859. Min Act: -0.0000

Data Index: 164998 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.4581. Min Act: -0.0000

Data Index: 72192 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.4513. Min Act: -0.0000

Data Index: 1074815 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.6248. Min Act: -0.0000

Data Index: 972579 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.4339. Min Act: -0.0000

Data Index: 40064 (C4 (Web Text))

Max Activating Token Index: 253

Text #11

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.4535. Min Act: -0.0000

Data Index: 942804 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.3900. Min Act: -0.0000

Data Index: 695237 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.3274. Min Act: -0.0000

Data Index: 1034667 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.3985. Min Act: -0.0000

Data Index: 931695 (C4 (Web Text))

Max Activating Token Index: 11

Text #15

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.3415. Min Act: -0.0000

Data Index: 1348842 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.4381. Min Act: -0.0000

Data Index: 913854 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.4017. Min Act: -0.0000

Data Index: 565891 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.1180. Min Act: -0.0000

Data Index: 995924 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 2.3867. Min Range: -2.3867

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1343458 (C4 (Web Text))

Max Activating Token Index: 150