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

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

Neuron 3255 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0864. Min Act: -0.0002

Data Index: 656009 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0685. Min Act: -0.0003

Data Index: 443883 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0654. Min Act: -0.0003

Data Index: 283619 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1170775 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0598. Min Act: -0.0002

Data Index: 644734 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0578. Min Act: -0.0002

Data Index: 955976 (C4 (Web Text))

Max Activating Token Index: 790

Text #6

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0629. Min Act: -0.0002

Data Index: 491348 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0548. Min Act: -0.0002

Data Index: 1309549 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0558. Min Act: -0.0002

Data Index: 577643 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0544. Min Act: -0.0002

Data Index: 731089 (C4 (Web Text))

Max Activating Token Index: 510

Text #10

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0492. Min Act: -0.0002

Data Index: 1208816 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0489. Min Act: -0.0002

Data Index: 680081 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0469. Min Act: -0.0003

Data Index: 236897 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0462. Min Act: -0.0002

Data Index: 601636 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0472. Min Act: -0.0003

Data Index: 709793 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0449. Min Act: -0.0002

Data Index: 941354 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0457. Min Act: -0.0002

Data Index: 904173 (C4 (Web Text))

Max Activating Token Index: 483

Text #17

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0437. Min Act: -0.0002

Data Index: 643489 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0461. Min Act: -0.0003

Data Index: 979244 (C4 (Web Text))

Max Activating Token Index: 298

Text #19

Max Range: 0.0864. Min Range: -0.0864

Max Act: 0.0427. Min Act: -0.0002

Data Index: 226589 (C4 (Web Text))

Max Activating Token Index: 704