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

Dataset: The Pile

Neuron 2268 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: 1.9768. Min Range: -1.9768

Max Act: 1.9768. Min Act: -0.0000

Data Index: 1472175 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3505. Min Act: -0.0000

Data Index: 551440 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.4264. Min Act: -0.0000

Data Index: 207538 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.4293. Min Act: -0.0000

Data Index: 109544 (The Pile)

Max Activating Token Index: 441

Text #4

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3456. Min Act: -0.0000

Data Index: 85626 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2618. Min Act: -0.0000

Data Index: 961012 (The Pile)

Max Activating Token Index: 252

Text #6

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3117. Min Act: -0.0000

Data Index: 127094 (The Pile)

Max Activating Token Index: 608

Text #7

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1472428 (The Pile)

Max Activating Token Index: 457

Text #8

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.0476. Min Act: -0.0000

Data Index: 650479 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3229. Min Act: -0.0000

Data Index: 343154 (The Pile)

Max Activating Token Index: 322

Text #10

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1178. Min Act: -0.0000

Data Index: 26490 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1439. Min Act: -0.0000

Data Index: 898924 (The Pile)

Max Activating Token Index: 496

Text #12

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1532. Min Act: -0.0000

Data Index: 1060026 (The Pile)

Max Activating Token Index: 791

Text #13

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3446. Min Act: -0.0000

Data Index: 166879 (The Pile)

Max Activating Token Index: 598

Text #14

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.3412. Min Act: -0.0000

Data Index: 1693227 (The Pile)

Max Activating Token Index: 809

Text #15

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1832. Min Act: -0.0000

Data Index: 165736 (The Pile)

Max Activating Token Index: 177

Text #16

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1942. Min Act: -0.0000

Data Index: 447576 (The Pile)

Max Activating Token Index: 78

Text #17

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1144504 (The Pile)

Max Activating Token Index: 120

Text #18

Max Range: 1.9768. Min Range: -1.9768

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1707230 (The Pile)

Max Activating Token Index: 634

Text #19

Max Range: 1.9768. Min Range: -1.9768

Max Act: 1.1404. Min Act: -0.0000

Data Index: 1268846 (The Pile)

Max Activating Token Index: 203