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

Dataset: The Pile

Neuron 2913 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: 5.9247. Min Range: -5.9247

Max Act: 5.9247. Min Act: -0.0000

Data Index: 1992231 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.2029. Min Act: -0.0000

Data Index: 538452 (The Pile)

Max Activating Token Index: 300

Text #2

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.8974. Min Act: -0.0000

Data Index: 451899 (The Pile)

Max Activating Token Index: 377

Text #3

Max Range: 5.9247. Min Range: -5.9247

Max Act: 5.0329. Min Act: -0.0000

Data Index: 827939 (The Pile)

Max Activating Token Index: 863

Text #4

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.2377. Min Act: -0.0000

Data Index: 360486 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.2646. Min Act: -0.0000

Data Index: 1894865 (The Pile)

Max Activating Token Index: 48

Text #6

Max Range: 5.9247. Min Range: -5.9247

Max Act: 4.0102. Min Act: -0.0000

Data Index: 1667325 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.7805. Min Act: -0.0000

Data Index: 809750 (The Pile)

Max Activating Token Index: 422

Text #8

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.6494. Min Act: -0.0000

Data Index: 638354 (The Pile)

Max Activating Token Index: 110

Text #9

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.7707. Min Act: -0.0000

Data Index: 369578 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.7544. Min Act: -0.0000

Data Index: 681370 (The Pile)

Max Activating Token Index: 316

Text #11

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.8908. Min Act: -0.0000

Data Index: 1266811 (The Pile)

Max Activating Token Index: 507

Text #12

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.7731. Min Act: -0.0000

Data Index: 197121 (The Pile)

Max Activating Token Index: 133

Text #13

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.5976. Min Act: -0.0000

Data Index: 1629242 (The Pile)

Max Activating Token Index: 142

Text #14

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.5865. Min Act: -0.0000

Data Index: 1128610 (The Pile)

Max Activating Token Index: 145

Text #15

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.4809. Min Act: -0.0000

Data Index: 627455 (The Pile)

Max Activating Token Index: 492

Text #16

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.5649. Min Act: -0.0000

Data Index: 1197475 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.4901. Min Act: -0.0000

Data Index: 1264202 (The Pile)

Max Activating Token Index: 143

Text #18

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.0003. Min Act: -0.0000

Data Index: 1159717 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 5.9247. Min Range: -5.9247

Max Act: 3.2666. Min Act: -0.0000

Data Index: 1434487 (The Pile)

Max Activating Token Index: 122