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

Dataset: The Pile

Neuron 2182 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1047. Min Act: -0.0000

Data Index: 1761985 (The Pile)

Max Activating Token Index: 783

Text #1

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1023. Min Act: -0.0000

Data Index: 646628 (The Pile)

Max Activating Token Index: 789

Text #2

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0570. Min Act: -0.0000

Data Index: 860641 (The Pile)

Max Activating Token Index: 749

Text #3

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.2410. Min Act: -0.0000

Data Index: 7918 (The Pile)

Max Activating Token Index: 431

Text #4

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0359. Min Act: -0.0000

Data Index: 1828268 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.0142. Min Act: -0.0000

Data Index: 332655 (The Pile)

Max Activating Token Index: 84

Text #6

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9399. Min Act: -0.0000

Data Index: 889235 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 1.2410. Min Range: -1.2410

Max Act: 1.1560. Min Act: -0.0000

Data Index: 1213258 (The Pile)

Max Activating Token Index: 801

Text #8

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.7158. Min Act: -0.0000

Data Index: 287533 (The Pile)

Max Activating Token Index: 704

Text #9

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9100. Min Act: -0.0000

Data Index: 67703 (The Pile)

Max Activating Token Index: 114

Text #10

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1496905 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9588. Min Act: -0.0000

Data Index: 547556 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8905. Min Act: -0.0000

Data Index: 1981851 (The Pile)

Max Activating Token Index: 640

Text #13

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.9106. Min Act: -0.0000

Data Index: 948331 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8364. Min Act: -0.0000

Data Index: 1477541 (The Pile)

Max Activating Token Index: 149

Text #15

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8769. Min Act: -0.0000

Data Index: 1370412 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8613. Min Act: -0.0000

Data Index: 1330941 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8066. Min Act: -0.0000

Data Index: 193953 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8233. Min Act: -0.0000

Data Index: 302096 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 1.2410. Min Range: -1.2410

Max Act: 0.8175. Min Act: -0.0000

Data Index: 1483512 (The Pile)

Max Activating Token Index: 690