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

Dataset: The Pile

Neuron 2046 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.3605. Min Act: -0.0000

Data Index: 237434 (The Pile)

Max Activating Token Index: 461

Text #1

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.1860. Min Act: -0.0000

Data Index: 854092 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.2727. Min Act: -0.0000

Data Index: 243765 (The Pile)

Max Activating Token Index: 167

Text #3

Max Range: 3.3605. Min Range: -3.3605

Max Act: 3.1440. Min Act: -0.0000

Data Index: 128376 (The Pile)

Max Activating Token Index: 394

Text #4

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.8893. Min Act: -0.0000

Data Index: 343783 (The Pile)

Max Activating Token Index: 681

Text #5

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.8034. Min Act: -0.0000

Data Index: 1433104 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.8277. Min Act: -0.0000

Data Index: 673458 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.9629. Min Act: -0.0000

Data Index: 79703 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.7735. Min Act: -0.0000

Data Index: 1767093 (The Pile)

Max Activating Token Index: 793

Text #9

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.7226. Min Act: -0.0000

Data Index: 681939 (The Pile)

Max Activating Token Index: 471

Text #10

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.7046. Min Act: -0.0000

Data Index: 499427 (The Pile)

Max Activating Token Index: 214

Text #11

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.6401. Min Act: -0.0000

Data Index: 1800579 (The Pile)

Max Activating Token Index: 286

Text #12

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.4424. Min Act: -0.0000

Data Index: 1728787 (The Pile)

Max Activating Token Index: 573

Text #13

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.5481. Min Act: -0.0000

Data Index: 367863 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.5724. Min Act: -0.0000

Data Index: 974503 (The Pile)

Max Activating Token Index: 144

Text #15

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.6735. Min Act: -0.0000

Data Index: 688729 (The Pile)

Max Activating Token Index: 990

Text #16

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.3727. Min Act: -0.0000

Data Index: 173896 (The Pile)

Max Activating Token Index: 737

Text #17

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.3759. Min Act: -0.0000

Data Index: 1063743 (The Pile)

Max Activating Token Index: 384

Text #18

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.3764. Min Act: -0.0000

Data Index: 445420 (The Pile)

Max Activating Token Index: 991

Text #19

Max Range: 3.3605. Min Range: -3.3605

Max Act: 2.4732. Min Act: -0.0000

Data Index: 1464690 (The Pile)

Max Activating Token Index: 176