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

Dataset: The Pile

Neuron 616 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: 1.5542. Min Range: -1.5542

Max Act: 1.3979. Min Act: -0.0000

Data Index: 1490879 (The Pile)

Max Activating Token Index: 488

Text #1

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.5542. Min Act: -0.0000

Data Index: 1117053 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.3682. Min Act: -0.0000

Data Index: 507726 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.4660. Min Act: -0.0000

Data Index: 1036002 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.2575. Min Act: -0.0000

Data Index: 1821203 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.3098. Min Act: -0.0000

Data Index: 82461 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.0959. Min Act: -0.0000

Data Index: 155140 (The Pile)

Max Activating Token Index: 290

Text #7

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.9910. Min Act: -0.0000

Data Index: 568725 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1147005 (The Pile)

Max Activating Token Index: 432

Text #9

Max Range: 1.5542. Min Range: -1.5542

Max Act: 1.0230. Min Act: 0.0000

Data Index: 575155 (The Pile)

Max Activating Token Index: 971

Text #10

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.8844. Min Act: -0.0000

Data Index: 1894080 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.9386. Min Act: -0.0000

Data Index: 746107 (The Pile)

Max Activating Token Index: 261

Text #12

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.9323. Min Act: -0.0000

Data Index: 1659828 (The Pile)

Max Activating Token Index: 130

Text #13

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1693930 (The Pile)

Max Activating Token Index: 547

Text #14

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.8658. Min Act: -0.0000

Data Index: 286126 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.9414. Min Act: -0.0000

Data Index: 1507105 (The Pile)

Max Activating Token Index: 740

Text #16

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.8904. Min Act: -0.0000

Data Index: 630839 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1978507 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.7562. Min Act: -0.0000

Data Index: 142266 (The Pile)

Max Activating Token Index: 718

Text #19

Max Range: 1.5542. Min Range: -1.5542

Max Act: 0.7882. Min Act: -0.0000

Data Index: 1591729 (The Pile)

Max Activating Token Index: 418