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

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

Neuron 1959 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.4904. Min Act: -0.0000

Data Index: 58664 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.3105. Min Act: -0.0000

Data Index: 432577 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.2373. Min Act: -0.0000

Data Index: 692987 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.1257. Min Act: -0.0000

Data Index: 566970 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 1.4904. Min Range: -1.4904

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1191243 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.7607. Min Act: -0.0000

Data Index: 413684 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.8339. Min Act: -0.0000

Data Index: 1153220 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1073292 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1014474 (C4 (Web Text))

Max Activating Token Index: 310

Text #9

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.7055. Min Act: -0.0000

Data Index: 925001 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6866. Min Act: -0.0000

Data Index: 188878 (C4 (Web Text))

Max Activating Token Index: 451

Text #11

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6670. Min Act: -0.0000

Data Index: 914584 (C4 (Web Text))

Max Activating Token Index: 138

Text #12

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6765. Min Act: -0.0000

Data Index: 470101 (C4 (Web Text))

Max Activating Token Index: 515

Text #13

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6654. Min Act: -0.0000

Data Index: 964266 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6857. Min Act: -0.0000

Data Index: 597489 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6633. Min Act: -0.0000

Data Index: 408946 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6832. Min Act: -0.0000

Data Index: 354615 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6601. Min Act: -0.0000

Data Index: 850544 (C4 (Web Text))

Max Activating Token Index: 637

Text #18

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.7119. Min Act: -0.0000

Data Index: 110657 (C4 (Web Text))

Max Activating Token Index: 243

Text #19

Max Range: 1.4904. Min Range: -1.4904

Max Act: 0.6251. Min Act: -0.0000

Data Index: 116092 (C4 (Web Text))

Max Activating Token Index: 81