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

Dataset: The Pile

Neuron 3844 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: 0.8128. Min Range: -0.8128

Max Act: 0.8029. Min Act: -0.0000

Data Index: 244746 (The Pile)

Max Activating Token Index: 544

Text #1

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.8128. Min Act: -0.0000

Data Index: 582049 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6874. Min Act: -0.0000

Data Index: 1365931 (The Pile)

Max Activating Token Index: 239

Text #3

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1080530 (The Pile)

Max Activating Token Index: 620

Text #4

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6478. Min Act: -0.0000

Data Index: 34537 (The Pile)

Max Activating Token Index: 113

Text #5

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5739. Min Act: -0.0000

Data Index: 63703 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6033. Min Act: -0.0000

Data Index: 1189148 (The Pile)

Max Activating Token Index: 154

Text #7

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5427. Min Act: -0.0000

Data Index: 665549 (The Pile)

Max Activating Token Index: 1010

Text #8

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1769900 (The Pile)

Max Activating Token Index: 436

Text #9

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5348. Min Act: -0.0000

Data Index: 108086 (The Pile)

Max Activating Token Index: 509

Text #10

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5400. Min Act: -0.0000

Data Index: 625727 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5526. Min Act: -0.0000

Data Index: 914739 (The Pile)

Max Activating Token Index: 966

Text #12

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.4968. Min Act: -0.0000

Data Index: 306301 (The Pile)

Max Activating Token Index: 983

Text #13

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.4421. Min Act: -0.0000

Data Index: 1881656 (The Pile)

Max Activating Token Index: 144

Text #14

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5247. Min Act: -0.0000

Data Index: 1014088 (The Pile)

Max Activating Token Index: 1012

Text #15

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5014. Min Act: -0.0000

Data Index: 1363378 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.6572. Min Act: -0.0000

Data Index: 1128699 (The Pile)

Max Activating Token Index: 609

Text #17

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5263. Min Act: -0.0000

Data Index: 1434038 (The Pile)

Max Activating Token Index: 495

Text #18

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5453. Min Act: -0.0000

Data Index: 1526738 (The Pile)

Max Activating Token Index: 877

Text #19

Max Range: 0.8128. Min Range: -0.8128

Max Act: 0.5285. Min Act: -0.0000

Data Index: 558637 (The Pile)

Max Activating Token Index: 995