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

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

Neuron 5675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.4953. Min Act: -0.0000

Data Index: 525440 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.4149. Min Act: -0.0000

Data Index: 396169 (C4 (Web Text))

Max Activating Token Index: 409

Text #2

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.4759. Min Act: -0.0000

Data Index: 700328 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3895. Min Act: -0.0000

Data Index: 286211 (C4 (Web Text))

Max Activating Token Index: 357

Text #4

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.2939. Min Act: -0.0000

Data Index: 860717 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3650. Min Act: -0.0000

Data Index: 594404 (C4 (Web Text))

Max Activating Token Index: 915

Text #6

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3422. Min Act: -0.0000

Data Index: 607651 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3773. Min Act: -0.0000

Data Index: 1125416 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3121. Min Act: -0.0000

Data Index: 1177433 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3676. Min Act: -0.0000

Data Index: 803958 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3399. Min Act: -0.0000

Data Index: 658795 (C4 (Web Text))

Max Activating Token Index: 664

Text #11

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3497. Min Act: -0.0000

Data Index: 881336 (C4 (Web Text))

Max Activating Token Index: 993

Text #12

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.2537. Min Act: -0.0000

Data Index: 825408 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.2584. Min Act: -0.0000

Data Index: 98962 (C4 (Web Text))

Max Activating Token Index: 654

Text #14

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3722. Min Act: -0.0000

Data Index: 57365 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.2939. Min Act: -0.0000

Data Index: 653411 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.2516. Min Act: -0.0000

Data Index: 1433347 (Python Code)

Max Activating Token Index: 715

Text #17

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.2453. Min Act: -0.0000

Data Index: 856051 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.2736. Min Act: -0.0000

Data Index: 1041157 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.4953. Min Range: -1.4953

Max Act: 1.3805. Min Act: -0.0000

Data Index: 1005724 (C4 (Web Text))

Max Activating Token Index: 332