Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2554 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.4024. Min Act: -0.0001

Data Index: 477746 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3533. Min Act: -0.0001

Data Index: 1284594 (C4 (Web Text))

Max Activating Token Index: 139

Text #2

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3347. Min Act: -0.0001

Data Index: 167464 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3005. Min Act: -0.0001

Data Index: 944401 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3029. Min Act: -0.0001

Data Index: 476336 (C4 (Web Text))

Max Activating Token Index: 333

Text #5

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3346. Min Act: -0.0001

Data Index: 1165845 (C4 (Web Text))

Max Activating Token Index: 52

Text #6

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3178. Min Act: -0.0001

Data Index: 694084 (C4 (Web Text))

Max Activating Token Index: 464

Text #7

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2911. Min Act: -0.0001

Data Index: 298328 (C4 (Web Text))

Max Activating Token Index: 536

Text #8

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.3020. Min Act: -0.0001

Data Index: 128334 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2779. Min Act: -0.0001

Data Index: 959436 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2969. Min Act: -0.0001

Data Index: 153101 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2938. Min Act: -0.0001

Data Index: 143518 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2745. Min Act: -0.0001

Data Index: 1149616 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2909. Min Act: -0.0001

Data Index: 1124371 (C4 (Web Text))

Max Activating Token Index: 605

Text #14

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2717. Min Act: -0.0001

Data Index: 2488 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2773. Min Act: -0.0001

Data Index: 59918 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2656. Min Act: -0.0001

Data Index: 1002059 (C4 (Web Text))

Max Activating Token Index: 912

Text #17

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2829. Min Act: -0.0001

Data Index: 378387 (C4 (Web Text))

Max Activating Token Index: 376

Text #18

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2707. Min Act: -0.0001

Data Index: 807797 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.4024. Min Range: -0.4024

Max Act: 0.2610. Min Act: -0.0001

Data Index: 702896 (C4 (Web Text))

Max Activating Token Index: 736