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

Dataset: The Pile

Neuron 877 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.5708. Min Act: -0.0000

Data Index: 583901 (The Pile)

Max Activating Token Index: 609

Text #1

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.6383. Min Act: -0.0000

Data Index: 554742 (The Pile)

Max Activating Token Index: 795

Text #2

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.4749. Min Act: -0.0000

Data Index: 415609 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.3854. Min Act: -0.0000

Data Index: 1389415 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.5323. Min Act: -0.0000

Data Index: 34230 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.3866. Min Act: -0.0000

Data Index: 1773513 (The Pile)

Max Activating Token Index: 893

Text #6

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.3849. Min Act: -0.0000

Data Index: 1468626 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2669. Min Act: -0.0000

Data Index: 1228119 (The Pile)

Max Activating Token Index: 194

Text #8

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2964. Min Act: -0.0000

Data Index: 1953312 (The Pile)

Max Activating Token Index: 456

Text #9

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2183. Min Act: -0.0000

Data Index: 468636 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2049. Min Act: -0.0000

Data Index: 1776756 (The Pile)

Max Activating Token Index: 439

Text #11

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2840. Min Act: -0.0000

Data Index: 387739 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2714. Min Act: -0.0000

Data Index: 1696000 (The Pile)

Max Activating Token Index: 942

Text #13

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1851. Min Act: -0.0000

Data Index: 28737 (The Pile)

Max Activating Token Index: 237

Text #14

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1693. Min Act: -0.0000

Data Index: 425077 (The Pile)

Max Activating Token Index: 460

Text #15

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2437. Min Act: -0.0000

Data Index: 1895747 (The Pile)

Max Activating Token Index: 368

Text #16

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.2092. Min Act: -0.0000

Data Index: 975811 (The Pile)

Max Activating Token Index: 831

Text #17

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1969. Min Act: -0.0000

Data Index: 450251 (The Pile)

Max Activating Token Index: 55

Text #18

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1895. Min Act: -0.0000

Data Index: 375078 (The Pile)

Max Activating Token Index: 29

Text #19

Max Range: 1.6383. Min Range: -1.6383

Max Act: 1.1156. Min Act: -0.0000

Data Index: 843652 (The Pile)

Max Activating Token Index: 611