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

Dataset: The Pile

Neuron 2484 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: 0.7168. Min Range: -0.7168

Max Act: 0.7168. Min Act: -0.0000

Data Index: 401830 (The Pile)

Max Activating Token Index: 715

Text #1

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5678. Min Act: -0.0000

Data Index: 674780 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5108. Min Act: -0.0000

Data Index: 546561 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6016. Min Act: 0.0000

Data Index: 1837368 (The Pile)

Max Activating Token Index: 154

Text #4

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6226. Min Act: 0.0000

Data Index: 1732500 (The Pile)

Max Activating Token Index: 259

Text #5

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6371. Min Act: -0.0000

Data Index: 1488608 (The Pile)

Max Activating Token Index: 329

Text #6

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.6109. Min Act: -0.0000

Data Index: 1351211 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4825. Min Act: -0.0000

Data Index: 636759 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4997. Min Act: 0.0000

Data Index: 1625120 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.5410. Min Act: 0.0000

Data Index: 1209983 (The Pile)

Max Activating Token Index: 383

Text #10

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4686. Min Act: -0.0000

Data Index: 802771 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4984. Min Act: -0.0000

Data Index: 1910314 (The Pile)

Max Activating Token Index: 421

Text #12

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1952461 (The Pile)

Max Activating Token Index: 24

Text #13

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4595. Min Act: 0.0000

Data Index: 496031 (The Pile)

Max Activating Token Index: 593

Text #14

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4811. Min Act: 0.0000

Data Index: 475927 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4329. Min Act: 0.0000

Data Index: 633101 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4206. Min Act: -0.0000

Data Index: 813667 (The Pile)

Max Activating Token Index: 686

Text #17

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4426. Min Act: -0.0000

Data Index: 901455 (The Pile)

Max Activating Token Index: 460

Text #18

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1657575 (The Pile)

Max Activating Token Index: 111

Text #19

Max Range: 0.7168. Min Range: -0.7168

Max Act: 0.4544. Min Act: -0.0000

Data Index: 367546 (The Pile)

Max Activating Token Index: 146