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

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

Neuron 956 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: 0.3583. Min Range: -0.3583

Max Act: 0.3554. Min Act: -0.0003

Data Index: 474154 (C4 (Web Text))

Max Activating Token Index: 995

Text #1

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.3583. Min Act: -0.0002

Data Index: 191390 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.3427. Min Act: -0.0004

Data Index: 622224 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2895. Min Act: -0.0003

Data Index: 445899 (C4 (Web Text))

Max Activating Token Index: 623

Text #4

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2766. Min Act: -0.0003

Data Index: 300445 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2765. Min Act: -0.0003

Data Index: 463839 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2684. Min Act: -0.0003

Data Index: 1108524 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2776. Min Act: -0.0003

Data Index: 550086 (C4 (Web Text))

Max Activating Token Index: 269

Text #8

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2454. Min Act: -0.0003

Data Index: 420539 (C4 (Web Text))

Max Activating Token Index: 271

Text #9

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2573. Min Act: -0.0003

Data Index: 1524061 (Python Code)

Max Activating Token Index: 187

Text #10

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2625. Min Act: -0.0003

Data Index: 251992 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2741. Min Act: -0.0003

Data Index: 760539 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2609. Min Act: -0.0003

Data Index: 1318842 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2517. Min Act: -0.0003

Data Index: 867109 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2693. Min Act: -0.0003

Data Index: 1309371 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2519. Min Act: -0.0003

Data Index: 267166 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2522. Min Act: -0.0003

Data Index: 765956 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2385. Min Act: -0.0003

Data Index: 1150563 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2281. Min Act: -0.0003

Data Index: 468405 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.3583. Min Range: -0.3583

Max Act: 0.2467. Min Act: -0.0002

Data Index: 330669 (C4 (Web Text))

Max Activating Token Index: 636