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

Dataset: The Pile

Neuron 2122 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5759. Min Act: -0.0000

Data Index: 378560 (The Pile)

Max Activating Token Index: 729

Text #1

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5652. Min Act: -0.0000

Data Index: 362112 (The Pile)

Max Activating Token Index: 720

Text #2

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5456. Min Act: -0.0000

Data Index: 895322 (The Pile)

Max Activating Token Index: 441

Text #3

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4565. Min Act: -0.0000

Data Index: 659403 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1239873 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4917. Min Act: -0.0000

Data Index: 522407 (The Pile)

Max Activating Token Index: 542

Text #6

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4873. Min Act: -0.0000

Data Index: 1857916 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4731. Min Act: -0.0000

Data Index: 1875196 (The Pile)

Max Activating Token Index: 340

Text #8

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4708. Min Act: -0.0000

Data Index: 928948 (The Pile)

Max Activating Token Index: 721

Text #9

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4882. Min Act: -0.0000

Data Index: 1066291 (The Pile)

Max Activating Token Index: 537

Text #10

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4677. Min Act: -0.0000

Data Index: 1552279 (The Pile)

Max Activating Token Index: 339

Text #11

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4819. Min Act: -0.0000

Data Index: 210228 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4384. Min Act: -0.0000

Data Index: 808006 (The Pile)

Max Activating Token Index: 376

Text #13

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4382. Min Act: -0.0000

Data Index: 940714 (The Pile)

Max Activating Token Index: 420

Text #14

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4003. Min Act: -0.0000

Data Index: 471420 (The Pile)

Max Activating Token Index: 688

Text #15

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3839. Min Act: -0.0000

Data Index: 1137960 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4738. Min Act: -0.0000

Data Index: 395951 (The Pile)

Max Activating Token Index: 691

Text #17

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3884. Min Act: -0.0000

Data Index: 622914 (The Pile)

Max Activating Token Index: 788

Text #18

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.4004. Min Act: -0.0000

Data Index: 1506152 (The Pile)

Max Activating Token Index: 941

Text #19

Max Range: 0.5759. Min Range: -0.5759

Max Act: 0.3914. Min Act: -0.0000

Data Index: 1737888 (The Pile)

Max Activating Token Index: 318