Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 420 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6388. Min Act: 0.0000

Data Index: 1102610 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6725. Min Act: -0.0000

Data Index: 908018 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6797. Min Act: -0.0000

Data Index: 1511336 (Python Code)

Max Activating Token Index: 998

Text #3

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6725. Min Act: -0.0000

Data Index: 857608 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6653. Min Act: -0.0000

Data Index: 428443 (C4 (Web Text))

Max Activating Token Index: 897

Text #5

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6492. Min Act: -0.0000

Data Index: 218192 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6123. Min Act: 0.0000

Data Index: 4776 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5943. Min Act: -0.0000

Data Index: 129247 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6060. Min Act: -0.0000

Data Index: 736793 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.6089. Min Act: -0.0000

Data Index: 1142892 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5831. Min Act: 0.0000

Data Index: 533825 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5687. Min Act: -0.0000

Data Index: 324352 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5529. Min Act: -0.0000

Data Index: 560622 (C4 (Web Text))

Max Activating Token Index: 684

Text #13

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5902. Min Act: -0.0000

Data Index: 511269 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5844. Min Act: -0.0000

Data Index: 11088 (C4 (Web Text))

Max Activating Token Index: 104

Text #15

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5422. Min Act: -0.0000

Data Index: 845166 (C4 (Web Text))

Max Activating Token Index: 1019

Text #16

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1128492 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5602. Min Act: -0.0000

Data Index: 1601161 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1304841 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 0.6797. Min Range: -0.6797

Max Act: 0.5747. Min Act: -0.0000

Data Index: 302156 (C4 (Web Text))

Max Activating Token Index: 102