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

Dataset: The Pile

Neuron 1390 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: 5.6484. Min Range: -5.6484

Max Act: 5.6484. Min Act: -0.0000

Data Index: 965228 (The Pile)

Max Activating Token Index: 714

Text #1

Max Range: 5.6484. Min Range: -5.6484

Max Act: 5.6378. Min Act: -0.0000

Data Index: 739560 (The Pile)

Max Activating Token Index: 438

Text #2

Max Range: 5.6484. Min Range: -5.6484

Max Act: 5.3228. Min Act: -0.0000

Data Index: 61548 (The Pile)

Max Activating Token Index: 348

Text #3

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.8451. Min Act: -0.0000

Data Index: 1042479 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 5.6484. Min Range: -5.6484

Max Act: 5.1829. Min Act: -0.0000

Data Index: 1142156 (The Pile)

Max Activating Token Index: 161

Text #5

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.6286. Min Act: -0.0000

Data Index: 1034632 (The Pile)

Max Activating Token Index: 405

Text #6

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.2675. Min Act: -0.0000

Data Index: 479995 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.6089. Min Act: -0.0000

Data Index: 519531 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.4159. Min Act: -0.0000

Data Index: 1642277 (The Pile)

Max Activating Token Index: 369

Text #9

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.3852. Min Act: -0.0000

Data Index: 894831 (The Pile)

Max Activating Token Index: 673

Text #10

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.8815. Min Act: -0.0000

Data Index: 1331572 (The Pile)

Max Activating Token Index: 962

Text #11

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.5283. Min Act: -0.0000

Data Index: 1948191 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.1776. Min Act: -0.0000

Data Index: 1154561 (The Pile)

Max Activating Token Index: 908

Text #13

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.5371. Min Act: -0.0000

Data Index: 794285 (The Pile)

Max Activating Token Index: 634

Text #14

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.1456. Min Act: -0.0000

Data Index: 1556846 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.2366. Min Act: -0.0000

Data Index: 1274710 (The Pile)

Max Activating Token Index: 189

Text #16

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.0787. Min Act: -0.0000

Data Index: 1505856 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 5.6484. Min Range: -5.6484

Max Act: 3.9923. Min Act: -0.0000

Data Index: 370685 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 5.6484. Min Range: -5.6484

Max Act: 3.7854. Min Act: -0.0000

Data Index: 1598813 (The Pile)

Max Activating Token Index: 108

Text #19

Max Range: 5.6484. Min Range: -5.6484

Max Act: 4.1300. Min Act: -0.0000

Data Index: 111489 (The Pile)

Max Activating Token Index: 894