Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 496 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.9000. Min Act: -0.0001

Data Index: 42044 (C4 (Web Text))

Max Activating Token Index: 449

Text #1

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.5940. Min Act: -0.0001

Data Index: 1031433 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.4365. Min Act: -0.0001

Data Index: 823969 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.4221. Min Act: -0.0001

Data Index: 85653 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.3335. Min Act: -0.0001

Data Index: 778207 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.7921. Min Act: -0.0001

Data Index: 158448 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.2472. Min Act: -0.0001

Data Index: 622147 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.3088. Min Act: -0.0001

Data Index: 113735 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.3240. Min Act: -0.0001

Data Index: 31824 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.2559. Min Act: -0.0001

Data Index: 645810 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.2627. Min Act: -0.0001

Data Index: 1080085 (C4 (Web Text))

Max Activating Token Index: 901

Text #11

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.2822. Min Act: -0.0001

Data Index: 607851 (C4 (Web Text))

Max Activating Token Index: 780

Text #12

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.2045. Min Act: -0.0001

Data Index: 883572 (C4 (Web Text))

Max Activating Token Index: 46

Text #13

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.2078. Min Act: -0.0001

Data Index: 1299152 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.1980. Min Act: -0.0001

Data Index: 457982 (C4 (Web Text))

Max Activating Token Index: 893

Text #15

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.1417. Min Act: -0.0001

Data Index: 730598 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.1701. Min Act: -0.0001

Data Index: 1347157 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.1512. Min Act: -0.0001

Data Index: 452711 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.2473. Min Act: -0.0001

Data Index: 427520 (C4 (Web Text))

Max Activating Token Index: 38

Text #19

Max Range: 1.9000. Min Range: -1.9000

Max Act: 1.0788. Min Act: -0.0001

Data Index: 200448 (C4 (Web Text))

Max Activating Token Index: 730