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

Dataset: The Pile

Neuron 616 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: 0.9065. Min Range: -0.9065

Max Act: 0.8214. Min Act: -0.0000

Data Index: 489090 (The Pile)

Max Activating Token Index: 823

Text #1

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.9065. Min Act: -0.0000

Data Index: 1536029 (The Pile)

Max Activating Token Index: 922

Text #2

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7803. Min Act: -0.0000

Data Index: 1718709 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7963. Min Act: -0.0000

Data Index: 254414 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7953. Min Act: -0.0000

Data Index: 1185127 (The Pile)

Max Activating Token Index: 795

Text #5

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6887. Min Act: -0.0000

Data Index: 854712 (The Pile)

Max Activating Token Index: 204

Text #6

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6888. Min Act: -0.0000

Data Index: 243001 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7260. Min Act: -0.0000

Data Index: 231039 (The Pile)

Max Activating Token Index: 761

Text #8

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1189446 (The Pile)

Max Activating Token Index: 191

Text #9

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7103. Min Act: -0.0000

Data Index: 580261 (The Pile)

Max Activating Token Index: 325

Text #10

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.7324. Min Act: -0.0000

Data Index: 841250 (The Pile)

Max Activating Token Index: 734

Text #11

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6505. Min Act: -0.0000

Data Index: 1573070 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6843. Min Act: -0.0000

Data Index: 896191 (The Pile)

Max Activating Token Index: 839

Text #13

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6253. Min Act: -0.0000

Data Index: 157436 (The Pile)

Max Activating Token Index: 440

Text #14

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6390. Min Act: -0.0000

Data Index: 1752539 (The Pile)

Max Activating Token Index: 870

Text #15

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6972. Min Act: -0.0000

Data Index: 827692 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6520. Min Act: -0.0000

Data Index: 1526194 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.5957. Min Act: -0.0000

Data Index: 116761 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6065. Min Act: -0.0000

Data Index: 1702947 (The Pile)

Max Activating Token Index: 690

Text #19

Max Range: 0.9065. Min Range: -0.9065

Max Act: 0.6489. Min Act: -0.0000

Data Index: 1128184 (The Pile)

Max Activating Token Index: 814