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

Dataset: The Pile

Neuron 4126 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.4333. Min Act: -0.0000

Data Index: 1039643 (The Pile)

Max Activating Token Index: 827

Text #1

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.4234. Min Act: -0.0000

Data Index: 732466 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.2738. Min Act: -0.0000

Data Index: 179531 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0414. Min Act: -0.0000

Data Index: 552253 (The Pile)

Max Activating Token Index: 291

Text #4

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1131126 (The Pile)

Max Activating Token Index: 461

Text #5

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.9914. Min Act: -0.0000

Data Index: 839091 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 1.4333. Min Range: -1.4333

Max Act: 1.0317. Min Act: -0.0000

Data Index: 599030 (The Pile)

Max Activating Token Index: 66

Text #7

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.9042. Min Act: -0.0000

Data Index: 1051631 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.9164. Min Act: -0.0000

Data Index: 1317624 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.9186. Min Act: -0.0000

Data Index: 856838 (The Pile)

Max Activating Token Index: 748

Text #10

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.9073. Min Act: -0.0000

Data Index: 1498505 (The Pile)

Max Activating Token Index: 348

Text #11

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1521081 (The Pile)

Max Activating Token Index: 605

Text #12

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1031267 (The Pile)

Max Activating Token Index: 874

Text #13

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.7612. Min Act: -0.0000

Data Index: 434672 (The Pile)

Max Activating Token Index: 929

Text #14

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.8942. Min Act: -0.0000

Data Index: 1326861 (The Pile)

Max Activating Token Index: 722

Text #15

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.8100. Min Act: -0.0000

Data Index: 182227 (The Pile)

Max Activating Token Index: 371

Text #16

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1342733 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1446712 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.8486. Min Act: -0.0000

Data Index: 177056 (The Pile)

Max Activating Token Index: 404

Text #19

Max Range: 1.4333. Min Range: -1.4333

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1547377 (The Pile)

Max Activating Token Index: 225