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

Dataset: The Pile

Neuron 3318 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: 0.3715. Min Range: -0.3715

Max Act: 0.3239. Min Act: -0.0000

Data Index: 1367513 (The Pile)

Max Activating Token Index: 952

Text #1

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3627. Min Act: -0.0000

Data Index: 234426 (The Pile)

Max Activating Token Index: 284

Text #2

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3508. Min Act: -0.0000

Data Index: 1219846 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3453. Min Act: -0.0000

Data Index: 1365793 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3271. Min Act: -0.0000

Data Index: 884801 (The Pile)

Max Activating Token Index: 115

Text #5

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2818. Min Act: -0.0000

Data Index: 304466 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.1071. Min Act: -0.0000

Data Index: 839468 (The Pile)

Max Activating Token Index: 858

Text #7

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3200. Min Act: -0.0000

Data Index: 1004304 (The Pile)

Max Activating Token Index: 167

Text #8

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1126753 (The Pile)

Max Activating Token Index: 564

Text #9

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3715. Min Act: -0.0000

Data Index: 1583573 (The Pile)

Max Activating Token Index: 825

Text #10

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3149. Min Act: -0.0000

Data Index: 533306 (The Pile)

Max Activating Token Index: 196

Text #11

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3124. Min Act: -0.0000

Data Index: 1443627 (The Pile)

Max Activating Token Index: 372

Text #12

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3071. Min Act: -0.0000

Data Index: 495748 (The Pile)

Max Activating Token Index: 440

Text #13

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.3043. Min Act: -0.0000

Data Index: 1286123 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.1465. Min Act: -0.0000

Data Index: 870690 (The Pile)

Max Activating Token Index: 104

Text #15

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1436590 (The Pile)

Max Activating Token Index: 358

Text #16

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2795. Min Act: -0.0000

Data Index: 252615 (The Pile)

Max Activating Token Index: 167

Text #17

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1266146 (The Pile)

Max Activating Token Index: 217

Text #18

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1132127 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 0.3715. Min Range: -0.3715

Max Act: 0.2987. Min Act: -0.0000

Data Index: 805133 (The Pile)

Max Activating Token Index: 453