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

Dataset: The Pile

Neuron 963 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1095102 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1564388 (The Pile)

Max Activating Token Index: 947

Text #2

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1150501 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1844893 (The Pile)

Max Activating Token Index: 1013

Text #4

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.6229. Min Act: -0.0000

Data Index: 89242 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1161228 (The Pile)

Max Activating Token Index: 132

Text #6

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5178. Min Act: -0.0000

Data Index: 48733 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5293. Min Act: -0.0000

Data Index: 1511296 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4889. Min Act: -0.0000

Data Index: 262242 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5214. Min Act: -0.0000

Data Index: 155404 (The Pile)

Max Activating Token Index: 997

Text #10

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1114176 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4837. Min Act: -0.0000

Data Index: 958423 (The Pile)

Max Activating Token Index: 213

Text #12

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.5367. Min Act: -0.0000

Data Index: 1722014 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4777. Min Act: -0.0000

Data Index: 605307 (The Pile)

Max Activating Token Index: 839

Text #14

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1266545 (The Pile)

Max Activating Token Index: 1017

Text #15

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4727. Min Act: -0.0000

Data Index: 225773 (The Pile)

Max Activating Token Index: 808

Text #16

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1209016 (The Pile)

Max Activating Token Index: 1003

Text #17

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4751. Min Act: -0.0000

Data Index: 266989 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4217. Min Act: -0.0000

Data Index: 2764 (The Pile)

Max Activating Token Index: 116

Text #19

Max Range: 0.6255. Min Range: -0.6255

Max Act: 0.4502. Min Act: -0.0000

Data Index: 1217726 (The Pile)

Max Activating Token Index: 672