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

Dataset: The Pile

Neuron 2161 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: 0.8270. Min Range: -0.8270

Max Act: 0.8270. Min Act: -0.0000

Data Index: 612303 (The Pile)

Max Activating Token Index: 600

Text #1

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.7523. Min Act: -0.0000

Data Index: 738994 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1996280 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5102. Min Act: -0.0000

Data Index: 1972071 (The Pile)

Max Activating Token Index: 401

Text #4

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4713. Min Act: -0.0000

Data Index: 509481 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1311663 (The Pile)

Max Activating Token Index: 168

Text #6

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4674. Min Act: -0.0000

Data Index: 1470858 (The Pile)

Max Activating Token Index: 371

Text #7

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4114. Min Act: -0.0000

Data Index: 363639 (The Pile)

Max Activating Token Index: 927

Text #8

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1757445 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4553. Min Act: -0.0000

Data Index: 639300 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4304. Min Act: -0.0000

Data Index: 647595 (The Pile)

Max Activating Token Index: 738

Text #11

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4685. Min Act: -0.0000

Data Index: 143026 (The Pile)

Max Activating Token Index: 345

Text #12

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4490. Min Act: -0.0000

Data Index: 1515357 (The Pile)

Max Activating Token Index: 803

Text #13

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4188. Min Act: -0.0000

Data Index: 1449659 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4427. Min Act: -0.0000

Data Index: 1632041 (The Pile)

Max Activating Token Index: 543

Text #15

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1160032 (The Pile)

Max Activating Token Index: 127

Text #16

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1159974 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4260. Min Act: -0.0000

Data Index: 106032 (The Pile)

Max Activating Token Index: 507

Text #18

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4067. Min Act: -0.0000

Data Index: 250532 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.8270. Min Range: -0.8270

Max Act: 0.4124. Min Act: -0.0000

Data Index: 380555 (The Pile)

Max Activating Token Index: 776