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

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

Neuron 1655 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3261. Min Act: -0.0000

Data Index: 195007 (C4 (Web Text))

Max Activating Token Index: 731

Text #1

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1040483 (C4 (Web Text))

Max Activating Token Index: 633

Text #2

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3298. Min Act: -0.0001

Data Index: 620398 (C4 (Web Text))

Max Activating Token Index: 961

Text #3

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3022. Min Act: -0.0001

Data Index: 688006 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2987. Min Act: -0.0000

Data Index: 103352 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3033. Min Act: -0.0001

Data Index: 1321530 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2902. Min Act: -0.0001

Data Index: 408483 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2994. Min Act: -0.0001

Data Index: 410266 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2851. Min Act: -0.0001

Data Index: 423850 (C4 (Web Text))

Max Activating Token Index: 634

Text #9

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2837. Min Act: -0.0000

Data Index: 1300564 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2969. Min Act: -0.0000

Data Index: 740466 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2754. Min Act: -0.0000

Data Index: 86309 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2733. Min Act: -0.0001

Data Index: 414369 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.3035. Min Act: -0.0000

Data Index: 206218 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2611. Min Act: -0.0000

Data Index: 1244050 (C4 (Web Text))

Max Activating Token Index: 953

Text #15

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2696. Min Act: -0.0001

Data Index: 328295 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2611. Min Act: -0.0000

Data Index: 810710 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2563. Min Act: -0.0000

Data Index: 579262 (C4 (Web Text))

Max Activating Token Index: 858

Text #18

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1491961 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.3335. Min Range: -0.3335

Max Act: 0.2521. Min Act: -0.0000

Data Index: 398514 (C4 (Web Text))

Max Activating Token Index: 776