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

Dataset: The Pile

Neuron 1761 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: 0.7275. Min Range: -0.7275

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1004173 (The Pile)

Max Activating Token Index: 553

Text #1

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.7194. Min Act: -0.0000

Data Index: 391214 (The Pile)

Max Activating Token Index: 190

Text #2

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6420. Min Act: -0.0000

Data Index: 1304766 (The Pile)

Max Activating Token Index: 959

Text #3

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1279443 (The Pile)

Max Activating Token Index: 86

Text #4

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6695. Min Act: -0.0000

Data Index: 1219557 (The Pile)

Max Activating Token Index: 774

Text #5

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6360. Min Act: -0.0000

Data Index: 1246094 (The Pile)

Max Activating Token Index: 26

Text #6

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6479. Min Act: -0.0000

Data Index: 954785 (The Pile)

Max Activating Token Index: 212

Text #7

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6052. Min Act: -0.0000

Data Index: 184676 (The Pile)

Max Activating Token Index: 187

Text #8

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6144. Min Act: -0.0000

Data Index: 1403944 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6033. Min Act: -0.0000

Data Index: 273216 (The Pile)

Max Activating Token Index: 711

Text #10

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6005. Min Act: -0.0000

Data Index: 1576301 (The Pile)

Max Activating Token Index: 271

Text #11

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6038. Min Act: -0.0000

Data Index: 704178 (The Pile)

Max Activating Token Index: 775

Text #12

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1270068 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.6124. Min Act: -0.0000

Data Index: 326491 (The Pile)

Max Activating Token Index: 588

Text #14

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5772. Min Act: -0.0000

Data Index: 198813 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1663842 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5730. Min Act: -0.0000

Data Index: 605441 (The Pile)

Max Activating Token Index: 978

Text #17

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5723. Min Act: -0.0000

Data Index: 1024676 (The Pile)

Max Activating Token Index: 434

Text #18

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1002523 (The Pile)

Max Activating Token Index: 190

Text #19

Max Range: 0.7275. Min Range: -0.7275

Max Act: 0.5679. Min Act: -0.0000

Data Index: 246582 (The Pile)

Max Activating Token Index: 110