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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 888 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.5666. Min Range: -2.5666

Max Act: 2.5216. Min Act: -0.0000

Data Index: 162232 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 2.5666. Min Range: -2.5666

Max Act: 2.5666. Min Act: -0.0000

Data Index: 594752 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 2.5666. Min Range: -2.5666

Max Act: 2.3484. Min Act: -0.0000

Data Index: 481739 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 2.5666. Min Range: -2.5666

Max Act: 2.2764. Min Act: -0.0000

Data Index: 1341976 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 2.5666. Min Range: -2.5666

Max Act: 2.0020. Min Act: -0.0000

Data Index: 1087539 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.9116. Min Act: -0.0000

Data Index: 233501 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.9038. Min Act: -0.0000

Data Index: 533272 (C4 (Web Text))

Max Activating Token Index: 984

Text #7

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.9640. Min Act: -0.0000

Data Index: 572776 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.7705. Min Act: -0.0000

Data Index: 777866 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.7081. Min Act: -0.0000

Data Index: 470536 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.8561. Min Act: -0.0000

Data Index: 404504 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.8375. Min Act: -0.0000

Data Index: 1240396 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.6476. Min Act: -0.0000

Data Index: 562756 (C4 (Web Text))

Max Activating Token Index: 323

Text #13

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.7078. Min Act: -0.0000

Data Index: 231589 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.7344. Min Act: -0.0000

Data Index: 32400 (C4 (Web Text))

Max Activating Token Index: 895

Text #15

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.6866. Min Act: -0.0000

Data Index: 185988 (C4 (Web Text))

Max Activating Token Index: 516

Text #16

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.6279. Min Act: -0.0000

Data Index: 580753 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.5224. Min Act: -0.0000

Data Index: 318744 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.5955. Min Act: -0.0000

Data Index: 413685 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 2.5666. Min Range: -2.5666

Max Act: 1.6510. Min Act: -0.0000

Data Index: 126410 (C4 (Web Text))

Max Activating Token Index: 155