Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 865 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0708. Min Act: -0.0003

Data Index: 1090456 (C4 (Web Text))

Max Activating Token Index: 907

Text #1

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0702. Min Act: -0.0002

Data Index: 773611 (C4 (Web Text))

Max Activating Token Index: 930

Text #2

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0501. Min Act: -0.0004

Data Index: 233099 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0469. Min Act: -0.0003

Data Index: 512789 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0477. Min Act: -0.0002

Data Index: 113421 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0478. Min Act: -0.0003

Data Index: 668942 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0485. Min Act: -0.0002

Data Index: 1049044 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1014062 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0474. Min Act: -0.0002

Data Index: 145545 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0485. Min Act: -0.0002

Data Index: 694970 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0462. Min Act: -0.0002

Data Index: 955426 (C4 (Web Text))

Max Activating Token Index: 907

Text #11

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0470. Min Act: -0.0002

Data Index: 633251 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0472. Min Act: -0.0002

Data Index: 960965 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0445. Min Act: -0.0002

Data Index: 929508 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0490. Min Act: -0.0002

Data Index: 306971 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0449. Min Act: -0.0003

Data Index: 690850 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1305871 (C4 (Web Text))

Max Activating Token Index: 536

Text #17

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0449. Min Act: -0.0002

Data Index: 990029 (C4 (Web Text))

Max Activating Token Index: 314

Text #18

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0459. Min Act: -0.0002

Data Index: 1217430 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0708. Min Range: -0.0708

Max Act: 0.0455. Min Act: -0.0002

Data Index: 981164 (C4 (Web Text))

Max Activating Token Index: 829