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

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

Neuron 1509 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.6034. Min Range: -8.6034

Max Act: 8.6034. Min Act: -0.0001

Data Index: 859171 (C4 (Web Text))

Max Activating Token Index: 260

Text #1

Max Range: 8.6034. Min Range: -8.6034

Max Act: 7.6609. Min Act: -0.0001

Data Index: 192568 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 8.6034. Min Range: -8.6034

Max Act: 7.7390. Min Act: -0.0001

Data Index: 337057 (C4 (Web Text))

Max Activating Token Index: 700

Text #3

Max Range: 8.6034. Min Range: -8.6034

Max Act: 7.7173. Min Act: -0.0001

Data Index: 958656 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 8.6034. Min Range: -8.6034

Max Act: 7.0719. Min Act: -0.0001

Data Index: 648400 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 8.6034. Min Range: -8.6034

Max Act: 7.4215. Min Act: -0.0001

Data Index: 885695 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 8.6034. Min Range: -8.6034

Max Act: 7.1732. Min Act: -0.0001

Data Index: 1101868 (C4 (Web Text))

Max Activating Token Index: 180

Text #7

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.9815. Min Act: -0.0001

Data Index: 1165967 (C4 (Web Text))

Max Activating Token Index: 511

Text #8

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.8211. Min Act: -0.0001

Data Index: 406506 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.9276. Min Act: -0.0001

Data Index: 177468 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.5218. Min Act: -0.0001

Data Index: 997202 (C4 (Web Text))

Max Activating Token Index: 380

Text #11

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.4393. Min Act: -0.0001

Data Index: 26959 (C4 (Web Text))

Max Activating Token Index: 962

Text #12

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.8871. Min Act: -0.0001

Data Index: 469787 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.4979. Min Act: -0.0001

Data Index: 571979 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 8.6034. Min Range: -8.6034

Max Act: 7.2010. Min Act: -0.0001

Data Index: 1242689 (C4 (Web Text))

Max Activating Token Index: 283

Text #15

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.6317. Min Act: -0.0001

Data Index: 1006067 (C4 (Web Text))

Max Activating Token Index: 355

Text #16

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.9535. Min Act: -0.0001

Data Index: 607506 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.7448. Min Act: -0.0001

Data Index: 619716 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.5333. Min Act: -0.0001

Data Index: 301353 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 8.6034. Min Range: -8.6034

Max Act: 6.5320. Min Act: -0.0001

Data Index: 589528 (C4 (Web Text))

Max Activating Token Index: 126