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

Dataset: The Pile

Neuron 3327 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.5222. Min Range: -8.5222

Max Act: 8.5222. Min Act: -0.0000

Data Index: 688603 (The Pile)

Max Activating Token Index: 179

Text #1

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.0852. Min Act: -0.0000

Data Index: 1451454 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 8.5222. Min Range: -8.5222

Max Act: 8.0245. Min Act: -0.0000

Data Index: 906781 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.8743. Min Act: -0.0000

Data Index: 750178 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.8660. Min Act: -0.0000

Data Index: 522512 (The Pile)

Max Activating Token Index: 246

Text #5

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.4603. Min Act: -0.0000

Data Index: 274416 (The Pile)

Max Activating Token Index: 720

Text #6

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.8830. Min Act: -0.0000

Data Index: 356195 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.1161. Min Act: -0.0000

Data Index: 1774558 (The Pile)

Max Activating Token Index: 143

Text #8

Max Range: 8.5222. Min Range: -8.5222

Max Act: 5.8922. Min Act: -0.0000

Data Index: 781466 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.0110. Min Act: -0.0000

Data Index: 915704 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 8.5222. Min Range: -8.5222

Max Act: 6.2314. Min Act: -0.0000

Data Index: 598033 (The Pile)

Max Activating Token Index: 608

Text #11

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.0761. Min Act: -0.0000

Data Index: 1923420 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.4316. Min Act: -0.0000

Data Index: 1970442 (The Pile)

Max Activating Token Index: 678

Text #13

Max Range: 8.5222. Min Range: -8.5222

Max Act: 6.5431. Min Act: -0.0000

Data Index: 1510130 (The Pile)

Max Activating Token Index: 339

Text #14

Max Range: 8.5222. Min Range: -8.5222

Max Act: 6.8291. Min Act: -0.0000

Data Index: 1396957 (The Pile)

Max Activating Token Index: 598

Text #15

Max Range: 8.5222. Min Range: -8.5222

Max Act: 7.1821. Min Act: -0.0000

Data Index: 1816107 (The Pile)

Max Activating Token Index: 667

Text #16

Max Range: 8.5222. Min Range: -8.5222

Max Act: 6.8390. Min Act: -0.0000

Data Index: 457028 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 8.5222. Min Range: -8.5222

Max Act: 6.4338. Min Act: -0.0000

Data Index: 610281 (The Pile)

Max Activating Token Index: 480

Text #18

Max Range: 8.5222. Min Range: -8.5222

Max Act: 6.9365. Min Act: -0.0000

Data Index: 1582912 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 8.5222. Min Range: -8.5222

Max Act: 6.5689. Min Act: -0.0000

Data Index: 1093682 (The Pile)

Max Activating Token Index: 222