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

Dataset: The Pile

Neuron 3352 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: 1.6314. Min Range: -1.6314

Max Act: 1.6314. Min Act: -0.0000

Data Index: 999432 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1313737 (The Pile)

Max Activating Token Index: 86

Text #2

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.6095. Min Act: -0.0000

Data Index: 852182 (The Pile)

Max Activating Token Index: 643

Text #3

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3789. Min Act: -0.0000

Data Index: 1702330 (The Pile)

Max Activating Token Index: 272

Text #4

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1228045 (The Pile)

Max Activating Token Index: 563

Text #5

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.4497. Min Act: -0.0000

Data Index: 100448 (The Pile)

Max Activating Token Index: 263

Text #6

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.4029. Min Act: -0.0000

Data Index: 220296 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.4339. Min Act: -0.0000

Data Index: 64807 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.4021. Min Act: -0.0000

Data Index: 1994018 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3780. Min Act: -0.0000

Data Index: 1563264 (The Pile)

Max Activating Token Index: 543

Text #10

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.4173. Min Act: -0.0000

Data Index: 1175709 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.4175. Min Act: -0.0000

Data Index: 1765897 (The Pile)

Max Activating Token Index: 480

Text #12

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3032. Min Act: -0.0000

Data Index: 1832244 (The Pile)

Max Activating Token Index: 56

Text #13

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1713321 (The Pile)

Max Activating Token Index: 993

Text #14

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3338. Min Act: -0.0000

Data Index: 180734 (The Pile)

Max Activating Token Index: 475

Text #15

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.2540. Min Act: -0.0000

Data Index: 40781 (The Pile)

Max Activating Token Index: 776

Text #16

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3765. Min Act: -0.0000

Data Index: 188177 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.3235. Min Act: -0.0000

Data Index: 1807324 (The Pile)

Max Activating Token Index: 985

Text #18

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.2398. Min Act: -0.0000

Data Index: 1526622 (The Pile)

Max Activating Token Index: 573

Text #19

Max Range: 1.6314. Min Range: -1.6314

Max Act: 1.4848. Min Act: -0.0000

Data Index: 1280177 (The Pile)

Max Activating Token Index: 825