Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 367 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1044047 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1875. Min Act: -0.0000

Data Index: 764476 (The Pile)

Max Activating Token Index: 537

Text #2

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0927. Min Act: -0.0000

Data Index: 77329 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1352319 (The Pile)

Max Activating Token Index: 266

Text #4

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1331. Min Act: -0.0000

Data Index: 397738 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0416. Min Act: -0.0000

Data Index: 970669 (The Pile)

Max Activating Token Index: 376

Text #6

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1253489 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.9644. Min Act: -0.0000

Data Index: 658466 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0420. Min Act: -0.0000

Data Index: 637506 (The Pile)

Max Activating Token Index: 55

Text #9

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1219760 (The Pile)

Max Activating Token Index: 753

Text #10

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.9617. Min Act: -0.0000

Data Index: 573344 (The Pile)

Max Activating Token Index: 370

Text #11

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0448. Min Act: -0.0000

Data Index: 120071 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.9568. Min Act: -0.0000

Data Index: 1720193 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 1.1875. Min Range: -1.1875

Max Act: 1.0250. Min Act: -0.0000

Data Index: 995783 (The Pile)

Max Activating Token Index: 624

Text #14

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.9628. Min Act: -0.0000

Data Index: 335089 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.8927. Min Act: -0.0000

Data Index: 1528690 (The Pile)

Max Activating Token Index: 362

Text #16

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.8147. Min Act: -0.0000

Data Index: 374735 (The Pile)

Max Activating Token Index: 580

Text #17

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1417899 (The Pile)

Max Activating Token Index: 652

Text #18

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.8559. Min Act: -0.0000

Data Index: 350850 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 1.1875. Min Range: -1.1875

Max Act: 0.8962. Min Act: -0.0000

Data Index: 836496 (The Pile)

Max Activating Token Index: 693