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

Dataset: The Pile

Neuron 2616 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: 5.0944. Min Range: -5.0944

Max Act: 5.0944. Min Act: -0.0000

Data Index: 911215 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 5.0944. Min Range: -5.0944

Max Act: 4.6865. Min Act: -0.0000

Data Index: 1862443 (The Pile)

Max Activating Token Index: 739

Text #2

Max Range: 5.0944. Min Range: -5.0944

Max Act: 4.2570. Min Act: -0.0000

Data Index: 1287233 (The Pile)

Max Activating Token Index: 657

Text #3

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.8702. Min Act: -0.0000

Data Index: 666876 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 5.0944. Min Range: -5.0944

Max Act: 4.2321. Min Act: -0.0000

Data Index: 648198 (The Pile)

Max Activating Token Index: 371

Text #5

Max Range: 5.0944. Min Range: -5.0944

Max Act: 4.3567. Min Act: -0.0000

Data Index: 595842 (The Pile)

Max Activating Token Index: 513

Text #6

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.9112. Min Act: -0.0000

Data Index: 619042 (The Pile)

Max Activating Token Index: 585

Text #7

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.6837. Min Act: -0.0000

Data Index: 902484 (The Pile)

Max Activating Token Index: 453

Text #8

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.8304. Min Act: -0.0000

Data Index: 1113975 (The Pile)

Max Activating Token Index: 289

Text #9

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.2880. Min Act: -0.0000

Data Index: 1563728 (The Pile)

Max Activating Token Index: 909

Text #10

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.6014. Min Act: -0.0000

Data Index: 1883264 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.9176. Min Act: -0.0000

Data Index: 392264 (The Pile)

Max Activating Token Index: 243

Text #12

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.4369. Min Act: -0.0000

Data Index: 1113705 (The Pile)

Max Activating Token Index: 719

Text #13

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.6992. Min Act: -0.0000

Data Index: 1428885 (The Pile)

Max Activating Token Index: 443

Text #14

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.6804. Min Act: -0.0000

Data Index: 896577 (The Pile)

Max Activating Token Index: 794

Text #15

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.6341. Min Act: -0.0000

Data Index: 382621 (The Pile)

Max Activating Token Index: 141

Text #16

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.5763. Min Act: -0.0000

Data Index: 172602 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.4531. Min Act: -0.0000

Data Index: 208235 (The Pile)

Max Activating Token Index: 684

Text #18

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.7786. Min Act: -0.0000

Data Index: 551871 (The Pile)

Max Activating Token Index: 543

Text #19

Max Range: 5.0944. Min Range: -5.0944

Max Act: 3.5022. Min Act: -0.0000

Data Index: 871023 (The Pile)

Max Activating Token Index: 238