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

Dataset: The Pile

Neuron 1794 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5945. Min Act: -0.0000

Data Index: 944077 (The Pile)

Max Activating Token Index: 230

Text #1

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5620. Min Act: -0.0000

Data Index: 192531 (The Pile)

Max Activating Token Index: 314

Text #2

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5172. Min Act: -0.0000

Data Index: 359696 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1203348 (The Pile)

Max Activating Token Index: 546

Text #4

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1838074 (The Pile)

Max Activating Token Index: 290

Text #5

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4963. Min Act: -0.0000

Data Index: 1702247 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5332. Min Act: -0.0000

Data Index: 385249 (The Pile)

Max Activating Token Index: 942

Text #7

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1074117 (The Pile)

Max Activating Token Index: 934

Text #8

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4762. Min Act: -0.0000

Data Index: 194666 (The Pile)

Max Activating Token Index: 669

Text #9

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4740. Min Act: -0.0000

Data Index: 121259 (The Pile)

Max Activating Token Index: 270

Text #10

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1307116 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4579. Min Act: -0.0000

Data Index: 1538748 (The Pile)

Max Activating Token Index: 56

Text #12

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4553. Min Act: -0.0000

Data Index: 609788 (The Pile)

Max Activating Token Index: 204

Text #13

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4406. Min Act: -0.0000

Data Index: 1440279 (The Pile)

Max Activating Token Index: 230

Text #14

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4385. Min Act: -0.0000

Data Index: 1233282 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4541. Min Act: -0.0000

Data Index: 932600 (The Pile)

Max Activating Token Index: 491

Text #16

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.5129. Min Act: -0.0000

Data Index: 693976 (The Pile)

Max Activating Token Index: 873

Text #17

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4523. Min Act: -0.0000

Data Index: 1132973 (The Pile)

Max Activating Token Index: 946

Text #18

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1885952 (The Pile)

Max Activating Token Index: 519

Text #19

Max Range: 0.5945. Min Range: -0.5945

Max Act: 0.4361. Min Act: -0.0000

Data Index: 752293 (The Pile)

Max Activating Token Index: 299