Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1330 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1245199 (The Pile)

Max Activating Token Index: 539

Text #1

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.6758. Min Act: -0.0000

Data Index: 1761365 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.6760. Min Act: -0.0000

Data Index: 574298 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5964. Min Act: -0.0000

Data Index: 1758977 (The Pile)

Max Activating Token Index: 613

Text #4

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.6523. Min Act: -0.0000

Data Index: 524235 (The Pile)

Max Activating Token Index: 519

Text #5

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.6796. Min Act: -0.0000

Data Index: 805363 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1232219 (The Pile)

Max Activating Token Index: 186

Text #7

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5358. Min Act: -0.0000

Data Index: 1258275 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5711. Min Act: -0.0000

Data Index: 1060360 (The Pile)

Max Activating Token Index: 390

Text #9

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5495. Min Act: -0.0000

Data Index: 362375 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1161950 (The Pile)

Max Activating Token Index: 222

Text #11

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1145828 (The Pile)

Max Activating Token Index: 460

Text #12

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5077. Min Act: -0.0000

Data Index: 1802251 (The Pile)

Max Activating Token Index: 259

Text #13

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5974. Min Act: -0.0000

Data Index: 954460 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5147. Min Act: -0.0000

Data Index: 1815814 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5433. Min Act: -0.0000

Data Index: 1061121 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5298. Min Act: -0.0000

Data Index: 899094 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5133. Min Act: -0.0000

Data Index: 714312 (The Pile)

Max Activating Token Index: 296

Text #18

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.5233. Min Act: -0.0000

Data Index: 707823 (The Pile)

Max Activating Token Index: 885

Text #19

Max Range: 0.7507. Min Range: -0.7507

Max Act: 0.4653. Min Act: -0.0000

Data Index: 1852556 (The Pile)

Max Activating Token Index: 723