Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1393 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2972. Min Act: -0.0002

Data Index: 1154416 (C4 (Web Text))

Max Activating Token Index: 811

Text #1

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2848. Min Act: -0.0002

Data Index: 380354 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2695. Min Act: -0.0002

Data Index: 843130 (C4 (Web Text))

Max Activating Token Index: 679

Text #3

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2760. Min Act: -0.0002

Data Index: 1207025 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2742. Min Act: -0.0002

Data Index: 1052747 (C4 (Web Text))

Max Activating Token Index: 131

Text #5

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2762. Min Act: -0.0002

Data Index: 1266333 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2526. Min Act: -0.0002

Data Index: 43357 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2628. Min Act: -0.0002

Data Index: 745644 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2587. Min Act: -0.0002

Data Index: 1328506 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2676. Min Act: -0.0002

Data Index: 909690 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2555. Min Act: -0.0002

Data Index: 1073183 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2663. Min Act: -0.0002

Data Index: 73732 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2552. Min Act: -0.0002

Data Index: 1136649 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2487. Min Act: -0.0002

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2602. Min Act: -0.0002

Data Index: 97223 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2502. Min Act: -0.0002

Data Index: 951522 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2417. Min Act: -0.0002

Data Index: 629688 (C4 (Web Text))

Max Activating Token Index: 400

Text #17

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2484. Min Act: -0.0002

Data Index: 218570 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2479. Min Act: -0.0002

Data Index: 614923 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.2972. Min Range: -0.2972

Max Act: 0.2551. Min Act: -0.0002

Data Index: 1236495 (C4 (Web Text))

Max Activating Token Index: 494