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

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

Neuron 4137 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1098. Min Act: -0.0002

Data Index: 91068 (C4 (Web Text))

Max Activating Token Index: 415

Text #1

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1288055 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1332740 (C4 (Web Text))

Max Activating Token Index: 382

Text #3

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1214818 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0763. Min Act: -0.0002

Data Index: 341858 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1156427 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0694. Min Act: -0.0002

Data Index: 1134096 (C4 (Web Text))

Max Activating Token Index: 958

Text #7

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1328957 (C4 (Web Text))

Max Activating Token Index: 939

Text #8

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0697. Min Act: -0.0002

Data Index: 215757 (C4 (Web Text))

Max Activating Token Index: 630

Text #9

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0696. Min Act: -0.0002

Data Index: 150604 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0634. Min Act: -0.0002

Data Index: 732091 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1241184 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0639. Min Act: -0.0002

Data Index: 966419 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0636. Min Act: -0.0002

Data Index: 665682 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0604. Min Act: -0.0002

Data Index: 673618 (C4 (Web Text))

Max Activating Token Index: 407

Text #15

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0605. Min Act: -0.0002

Data Index: 778921 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0578. Min Act: -0.0002

Data Index: 325553 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0602. Min Act: -0.0002

Data Index: 302113 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0591. Min Act: -0.0002

Data Index: 112793 (C4 (Web Text))

Max Activating Token Index: 121

Text #19

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0607. Min Act: -0.0002

Data Index: 683005 (C4 (Web Text))

Max Activating Token Index: 845