Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2805 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2816. Min Act: -0.0001

Data Index: 1023098 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2492. Min Act: -0.0001

Data Index: 340955 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2397. Min Act: -0.0001

Data Index: 280152 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2324. Min Act: -0.0001

Data Index: 787553 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2296. Min Act: -0.0001

Data Index: 684379 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2244. Min Act: -0.0001

Data Index: 201917 (C4 (Web Text))

Max Activating Token Index: 849

Text #6

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2304. Min Act: -0.0001

Data Index: 966444 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.2151. Min Act: -0.0001

Data Index: 1093242 (C4 (Web Text))

Max Activating Token Index: 684

Text #8

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1973. Min Act: -0.0001

Data Index: 343901 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1895. Min Act: -0.0001

Data Index: 664075 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1816. Min Act: -0.0001

Data Index: 289991 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1599. Min Act: -0.0001

Data Index: 339327 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1764. Min Act: -0.0001

Data Index: 1130433 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1240403 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1609. Min Act: -0.0001

Data Index: 345118 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1047685 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1614. Min Act: -0.0001

Data Index: 1022537 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1631. Min Act: -0.0001

Data Index: 13041 (C4 (Web Text))

Max Activating Token Index: 736

Text #18

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1560. Min Act: -0.0001

Data Index: 906110 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.2816. Min Range: -0.2816

Max Act: 0.1497. Min Act: -0.0001

Data Index: 453233 (C4 (Web Text))

Max Activating Token Index: 668