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

Dataset: The Pile

Neuron 2068 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.2923. Min Act: -0.0000

Data Index: 1698253 (The Pile)

Max Activating Token Index: 305

Text #1

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.2379. Min Act: -0.0000

Data Index: 753806 (The Pile)

Max Activating Token Index: 973

Text #2

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1223. Min Act: -0.0000

Data Index: 436666 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1740. Min Act: -0.0000

Data Index: 844454 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.3175. Min Act: -0.0000

Data Index: 242282 (The Pile)

Max Activating Token Index: 893

Text #5

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1314. Min Act: -0.0000

Data Index: 997663 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1176. Min Act: -0.0000

Data Index: 1090855 (The Pile)

Max Activating Token Index: 849

Text #7

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.3067. Min Act: -0.0000

Data Index: 1834559 (The Pile)

Max Activating Token Index: 632

Text #8

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1613. Min Act: -0.0000

Data Index: 1279466 (The Pile)

Max Activating Token Index: 585

Text #9

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.2271. Min Act: -0.0000

Data Index: 74797 (The Pile)

Max Activating Token Index: 722

Text #10

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1440. Min Act: -0.0000

Data Index: 1104176 (The Pile)

Max Activating Token Index: 699

Text #11

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1075. Min Act: -0.0000

Data Index: 1622774 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1410. Min Act: -0.0000

Data Index: 1030667 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1732. Min Act: -0.0000

Data Index: 1718457 (The Pile)

Max Activating Token Index: 880

Text #14

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0882. Min Act: -0.0000

Data Index: 1642955 (The Pile)

Max Activating Token Index: 251

Text #15

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1673355 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0162. Min Act: -0.0000

Data Index: 833387 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9931. Min Act: -0.0000

Data Index: 290545 (The Pile)

Max Activating Token Index: 475

Text #18

Max Range: 1.3175. Min Range: -1.3175

Max Act: 0.9437. Min Act: -0.0000

Data Index: 725169 (The Pile)

Max Activating Token Index: 849

Text #19

Max Range: 1.3175. Min Range: -1.3175

Max Act: 1.0728. Min Act: -0.0000

Data Index: 515054 (The Pile)

Max Activating Token Index: 568