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

Dataset: The Pile

Neuron 3781 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: 1.1310. Min Range: -1.1310

Max Act: 1.0675. Min Act: -0.0000

Data Index: 464278 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1681391 (The Pile)

Max Activating Token Index: 796

Text #2

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.1032. Min Act: -0.0000

Data Index: 186314 (The Pile)

Max Activating Token Index: 501

Text #3

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.0357. Min Act: -0.0000

Data Index: 1496693 (The Pile)

Max Activating Token Index: 351

Text #4

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.1170. Min Act: -0.0000

Data Index: 55005 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.0538. Min Act: -0.0000

Data Index: 571828 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9843. Min Act: -0.0000

Data Index: 1467687 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.0721. Min Act: -0.0000

Data Index: 667069 (The Pile)

Max Activating Token Index: 602

Text #8

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9982. Min Act: -0.0000

Data Index: 1069260 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9942. Min Act: -0.0000

Data Index: 3152 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9093. Min Act: -0.0000

Data Index: 188854 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9776. Min Act: -0.0000

Data Index: 1497425 (The Pile)

Max Activating Token Index: 271

Text #12

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9747. Min Act: -0.0000

Data Index: 849688 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9435. Min Act: -0.0000

Data Index: 1375363 (The Pile)

Max Activating Token Index: 422

Text #14

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9747. Min Act: -0.0000

Data Index: 392294 (The Pile)

Max Activating Token Index: 280

Text #15

Max Range: 1.1310. Min Range: -1.1310

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1070476 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8694. Min Act: -0.0000

Data Index: 1943790 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8459. Min Act: -0.0000

Data Index: 70408 (The Pile)

Max Activating Token Index: 847

Text #18

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.8425. Min Act: -0.0000

Data Index: 1269015 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 1.1310. Min Range: -1.1310

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1569926 (The Pile)

Max Activating Token Index: 417