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

Dataset: The Pile

Neuron 3371 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: 0.9829. Min Range: -0.9829

Max Act: 0.8826. Min Act: -0.0000

Data Index: 726269 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9829. Min Act: -0.0000

Data Index: 145814 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9582. Min Act: -0.0000

Data Index: 892534 (The Pile)

Max Activating Token Index: 907

Text #3

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9470. Min Act: -0.0000

Data Index: 958163 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1009116 (The Pile)

Max Activating Token Index: 416

Text #5

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8988. Min Act: -0.0000

Data Index: 1861786 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1833712 (The Pile)

Max Activating Token Index: 404

Text #7

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7812. Min Act: -0.0000

Data Index: 1312199 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1686661 (The Pile)

Max Activating Token Index: 233

Text #9

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7936. Min Act: -0.0000

Data Index: 1388039 (The Pile)

Max Activating Token Index: 994

Text #10

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.8552. Min Act: -0.0000

Data Index: 914114 (The Pile)

Max Activating Token Index: 135

Text #11

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7998. Min Act: -0.0000

Data Index: 492006 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1310555 (The Pile)

Max Activating Token Index: 940

Text #13

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7410. Min Act: -0.0000

Data Index: 810793 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7857. Min Act: -0.0000

Data Index: 624070 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1443950 (The Pile)

Max Activating Token Index: 68

Text #16

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1386508 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7661. Min Act: -0.0000

Data Index: 966725 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7571. Min Act: -0.0000

Data Index: 655690 (The Pile)

Max Activating Token Index: 920

Text #19

Max Range: 0.9829. Min Range: -0.9829

Max Act: 0.7637. Min Act: -0.0000

Data Index: 79271 (The Pile)

Max Activating Token Index: 819