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

Dataset: The Pile

Neuron 2478 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6662. Min Act: -0.0000

Data Index: 21451 (The Pile)

Max Activating Token Index: 734

Text #1

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.7759. Min Act: -0.0000

Data Index: 466394 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6641. Min Act: -0.0000

Data Index: 739858 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5457. Min Act: -0.0000

Data Index: 1230889 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4019. Min Act: -0.0000

Data Index: 982549 (The Pile)

Max Activating Token Index: 768

Text #5

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1295999 (The Pile)

Max Activating Token Index: 819

Text #6

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.6103. Min Act: -0.0000

Data Index: 1483175 (The Pile)

Max Activating Token Index: 447

Text #7

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1082106 (The Pile)

Max Activating Token Index: 750

Text #8

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5554. Min Act: -0.0000

Data Index: 650907 (The Pile)

Max Activating Token Index: 536

Text #9

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4321. Min Act: -0.0000

Data Index: 544253 (The Pile)

Max Activating Token Index: 176

Text #10

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4654. Min Act: -0.0000

Data Index: 35745 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1712702 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4737. Min Act: -0.0000

Data Index: 975059 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.5153. Min Act: -0.0000

Data Index: 650199 (The Pile)

Max Activating Token Index: 679

Text #14

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4172. Min Act: -0.0000

Data Index: 108250 (The Pile)

Max Activating Token Index: 213

Text #15

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4572. Min Act: -0.0000

Data Index: 481044 (The Pile)

Max Activating Token Index: 611

Text #16

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.3874. Min Act: -0.0000

Data Index: 122225 (The Pile)

Max Activating Token Index: 236

Text #17

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1511211 (The Pile)

Max Activating Token Index: 1000

Text #18

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4341. Min Act: -0.0000

Data Index: 556800 (The Pile)

Max Activating Token Index: 100

Text #19

Max Range: 0.7759. Min Range: -0.7759

Max Act: 0.4633. Min Act: -0.0000

Data Index: 1266918 (The Pile)

Max Activating Token Index: 953