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

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

Neuron 1990 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: 3.3263. Min Range: -3.3263

Max Act: 3.3263. Min Act: -0.0000

Data Index: 171339 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.5520. Min Act: -0.0000

Data Index: 103666 (C4 (Web Text))

Max Activating Token Index: 344

Text #2

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.8081. Min Act: -0.0000

Data Index: 1347106 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.4556. Min Act: -0.0000

Data Index: 497308 (C4 (Web Text))

Max Activating Token Index: 704

Text #4

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.4484. Min Act: -0.0000

Data Index: 250729 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.5392. Min Act: -0.0000

Data Index: 976476 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.3989. Min Act: -0.0000

Data Index: 318991 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.4549. Min Act: -0.0000

Data Index: 99782 (C4 (Web Text))

Max Activating Token Index: 275

Text #8

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.4049. Min Act: -0.0000

Data Index: 1411747 (Python Code)

Max Activating Token Index: 705

Text #9

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.5163. Min Act: -0.0000

Data Index: 648695 (C4 (Web Text))

Max Activating Token Index: 476

Text #10

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.1510. Min Act: -0.0000

Data Index: 694492 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.3828. Min Act: -0.0000

Data Index: 337214 (C4 (Web Text))

Max Activating Token Index: 65

Text #12

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.3491. Min Act: -0.0000

Data Index: 530351 (C4 (Web Text))

Max Activating Token Index: 137

Text #13

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.4384. Min Act: -0.0000

Data Index: 1204804 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.3099. Min Act: -0.0000

Data Index: 1340860 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.3039. Min Act: -0.0000

Data Index: 1513368 (Python Code)

Max Activating Token Index: 63

Text #16

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.2978. Min Act: -0.0000

Data Index: 398000 (C4 (Web Text))

Max Activating Token Index: 881

Text #17

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.2878. Min Act: -0.0000

Data Index: 50155 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.2938. Min Act: -0.0000

Data Index: 691303 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 3.3263. Min Range: -3.3263

Max Act: 2.2849. Min Act: -0.0000

Data Index: 858591 (C4 (Web Text))

Max Activating Token Index: 40