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

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

Neuron 2406 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.4161. Min Act: -0.0001

Data Index: 1119186 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.2485. Min Act: -0.0001

Data Index: 1206898 (C4 (Web Text))

Max Activating Token Index: 135

Text #2

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.2571. Min Act: -0.0001

Data Index: 192191 (C4 (Web Text))

Max Activating Token Index: 499

Text #3

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.1071. Min Act: -0.0001

Data Index: 877530 (C4 (Web Text))

Max Activating Token Index: 212

Text #4

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.1280. Min Act: -0.0001

Data Index: 1187439 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.1991. Min Act: -0.0001

Data Index: 814598 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.2577. Min Act: -0.0001

Data Index: 163739 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.1909. Min Act: -0.0001

Data Index: 123411 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0871. Min Act: -0.0001

Data Index: 46113 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0383. Min Act: -0.0001

Data Index: 84765 (C4 (Web Text))

Max Activating Token Index: 517

Text #10

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0682. Min Act: -0.0001

Data Index: 421632 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0095. Min Act: -0.0001

Data Index: 818225 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.1482. Min Act: -0.0001

Data Index: 799798 (C4 (Web Text))

Max Activating Token Index: 234

Text #13

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0615. Min Act: -0.0001

Data Index: 361575 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.1044. Min Act: -0.0001

Data Index: 596473 (C4 (Web Text))

Max Activating Token Index: 985

Text #15

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.1222. Min Act: -0.0001

Data Index: 535393 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0609. Min Act: -0.0001

Data Index: 50180 (C4 (Web Text))

Max Activating Token Index: 870

Text #17

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0592. Min Act: -0.0001

Data Index: 296588 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0874. Min Act: -0.0001

Data Index: 154397 (C4 (Web Text))

Max Activating Token Index: 696

Text #19

Max Range: 1.4161. Min Range: -1.4161

Max Act: 1.0182. Min Act: -0.0001

Data Index: 968951 (C4 (Web Text))

Max Activating Token Index: 515