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

Dataset: The Pile

Neuron 4242 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: 0.7230. Min Range: -0.7230

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1354701 (The Pile)

Max Activating Token Index: 892

Text #1

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.7138. Min Act: -0.0000

Data Index: 783545 (The Pile)

Max Activating Token Index: 687

Text #2

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.7230. Min Act: -0.0000

Data Index: 523079 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6504. Min Act: -0.0000

Data Index: 1317390 (The Pile)

Max Activating Token Index: 792

Text #4

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.7176. Min Act: -0.0000

Data Index: 973693 (The Pile)

Max Activating Token Index: 122

Text #5

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6732. Min Act: -0.0000

Data Index: 525814 (The Pile)

Max Activating Token Index: 444

Text #6

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6735. Min Act: -0.0000

Data Index: 834498 (The Pile)

Max Activating Token Index: 78

Text #7

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6512. Min Act: -0.0000

Data Index: 332838 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6804. Min Act: -0.0000

Data Index: 1181096 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1300270 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6830. Min Act: -0.0000

Data Index: 222643 (The Pile)

Max Activating Token Index: 763

Text #11

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6699. Min Act: -0.0000

Data Index: 1669584 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6670. Min Act: -0.0000

Data Index: 968858 (The Pile)

Max Activating Token Index: 843

Text #13

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1757769 (The Pile)

Max Activating Token Index: 391

Text #14

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6146. Min Act: -0.0000

Data Index: 683065 (The Pile)

Max Activating Token Index: 249

Text #15

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6636. Min Act: -0.0000

Data Index: 1473687 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1080098 (The Pile)

Max Activating Token Index: 359

Text #17

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5701. Min Act: -0.0000

Data Index: 467716 (The Pile)

Max Activating Token Index: 971

Text #18

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5613. Min Act: 0.0000

Data Index: 618 (The Pile)

Max Activating Token Index: 88

Text #19

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5789. Min Act: -0.0000

Data Index: 65612 (The Pile)

Max Activating Token Index: 331