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

Dataset: The Pile

Neuron 1548 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.6119. Min Act: -0.0000

Data Index: 1806710 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1214957 (The Pile)

Max Activating Token Index: 737

Text #2

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4946. Min Act: -0.0000

Data Index: 377207 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4838. Min Act: -0.0000

Data Index: 581919 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4455. Min Act: -0.0000

Data Index: 518698 (The Pile)

Max Activating Token Index: 1004

Text #5

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4675. Min Act: -0.0000

Data Index: 1127517 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4235. Min Act: -0.0000

Data Index: 871085 (The Pile)

Max Activating Token Index: 558

Text #7

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4324. Min Act: -0.0000

Data Index: 980210 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4275. Min Act: -0.0000

Data Index: 907307 (The Pile)

Max Activating Token Index: 953

Text #9

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4129. Min Act: -0.0000

Data Index: 66499 (The Pile)

Max Activating Token Index: 302

Text #10

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3877. Min Act: -0.0000

Data Index: 1625782 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4133. Min Act: -0.0000

Data Index: 162442 (The Pile)

Max Activating Token Index: 450

Text #12

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.4279. Min Act: -0.0000

Data Index: 1051882 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3977. Min Act: -0.0000

Data Index: 560508 (The Pile)

Max Activating Token Index: 948

Text #14

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3992. Min Act: -0.0000

Data Index: 769153 (The Pile)

Max Activating Token Index: 820

Text #15

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3935. Min Act: -0.0000

Data Index: 1777427 (The Pile)

Max Activating Token Index: 794

Text #16

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1992003 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3818. Min Act: -0.0000

Data Index: 1000696 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1276193 (The Pile)

Max Activating Token Index: 885

Text #19

Max Range: 0.6119. Min Range: -0.6119

Max Act: 0.3758. Min Act: -0.0000

Data Index: 468446 (The Pile)

Max Activating Token Index: 863