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

Dataset: The Pile

Neuron 778 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: 0.6307. Min Range: -0.6307

Max Act: 0.6246. Min Act: -0.0000

Data Index: 942369 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.6307. Min Act: 0.0000

Data Index: 1031430 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5691. Min Act: -0.0000

Data Index: 28530 (The Pile)

Max Activating Token Index: 67

Text #3

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.6233. Min Act: 0.0000

Data Index: 1511081 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5596. Min Act: -0.0000

Data Index: 99428 (The Pile)

Max Activating Token Index: 803

Text #5

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5561. Min Act: 0.0000

Data Index: 1405457 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1950349 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1624697 (The Pile)

Max Activating Token Index: 436

Text #8

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5288. Min Act: -0.0000

Data Index: 1336589 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5365. Min Act: -0.0000

Data Index: 1850481 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1921473 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5038. Min Act: -0.0000

Data Index: 1423707 (The Pile)

Max Activating Token Index: 92

Text #12

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1002816 (The Pile)

Max Activating Token Index: 527

Text #13

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5194. Min Act: -0.0000

Data Index: 1048311 (The Pile)

Max Activating Token Index: 461

Text #14

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5345. Min Act: 0.0000

Data Index: 980634 (The Pile)

Max Activating Token Index: 133

Text #15

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4902. Min Act: -0.0000

Data Index: 805761 (The Pile)

Max Activating Token Index: 243

Text #16

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1936089 (The Pile)

Max Activating Token Index: 616

Text #17

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1536092 (The Pile)

Max Activating Token Index: 114

Text #18

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4717. Min Act: 0.0000

Data Index: 879698 (The Pile)

Max Activating Token Index: 475

Text #19

Max Range: 0.6307. Min Range: -0.6307

Max Act: 0.4799. Min Act: -0.0000

Data Index: 1361517 (The Pile)

Max Activating Token Index: 900