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

Dataset: The Pile

Neuron 1226 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: 1.0370. Min Range: -1.0370

Max Act: 1.0370. Min Act: -0.0000

Data Index: 430828 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.7842. Min Act: -0.0000

Data Index: 749035 (The Pile)

Max Activating Token Index: 548

Text #2

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.7984. Min Act: -0.0000

Data Index: 319187 (The Pile)

Max Activating Token Index: 635

Text #3

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1975045 (The Pile)

Max Activating Token Index: 312

Text #4

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1539890 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6933. Min Act: -0.0000

Data Index: 572126 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6416. Min Act: -0.0000

Data Index: 725251 (The Pile)

Max Activating Token Index: 145

Text #7

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6141. Min Act: -0.0000

Data Index: 81077 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6760. Min Act: -0.0000

Data Index: 188404 (The Pile)

Max Activating Token Index: 380

Text #9

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1256939 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1685593 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6028. Min Act: -0.0000

Data Index: 1866887 (The Pile)

Max Activating Token Index: 240

Text #12

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.5050. Min Act: -0.0000

Data Index: 1789154 (The Pile)

Max Activating Token Index: 806

Text #13

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.5496. Min Act: -0.0000

Data Index: 359538 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.5575. Min Act: -0.0000

Data Index: 636702 (The Pile)

Max Activating Token Index: 685

Text #15

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1579631 (The Pile)

Max Activating Token Index: 789

Text #16

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.5668. Min Act: -0.0000

Data Index: 1701528 (The Pile)

Max Activating Token Index: 204

Text #17

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.5468. Min Act: -0.0000

Data Index: 791273 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.4922. Min Act: -0.0000

Data Index: 1166693 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 1.0370. Min Range: -1.0370

Max Act: 0.5282. Min Act: -0.0000

Data Index: 448150 (The Pile)

Max Activating Token Index: 85