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

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

Neuron 2185 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8773. Min Act: -0.0000

Data Index: 134464 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8917. Min Act: -0.0000

Data Index: 343834 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8435. Min Act: -0.0000

Data Index: 109029 (C4 (Web Text))

Max Activating Token Index: 411

Text #3

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8283. Min Act: -0.0000

Data Index: 1045898 (C4 (Web Text))

Max Activating Token Index: 102

Text #4

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8356. Min Act: -0.0000

Data Index: 177239 (C4 (Web Text))

Max Activating Token Index: 757

Text #5

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8303. Min Act: -0.0000

Data Index: 786893 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7673. Min Act: -0.0000

Data Index: 554997 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.8493. Min Act: -0.0000

Data Index: 724496 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7270. Min Act: -0.0000

Data Index: 887128 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.7378. Min Act: -0.0000

Data Index: 1440146 (Python Code)

Max Activating Token Index: 139

Text #10

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6978. Min Act: -0.0000

Data Index: 965246 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6751. Min Act: -0.0000

Data Index: 1491180 (Python Code)

Max Activating Token Index: 378

Text #12

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6874. Min Act: -0.0000

Data Index: 963228 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1507226 (Python Code)

Max Activating Token Index: 1022

Text #14

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6598. Min Act: -0.0000

Data Index: 370341 (C4 (Web Text))

Max Activating Token Index: 759

Text #15

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1399498 (Python Code)

Max Activating Token Index: 525

Text #16

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6838. Min Act: -0.0000

Data Index: 918244 (C4 (Web Text))

Max Activating Token Index: 109

Text #17

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1136660 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6650. Min Act: -0.0000

Data Index: 27054 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.8917. Min Range: -0.8917

Max Act: 0.6437. Min Act: -0.0000

Data Index: 1530497 (Python Code)

Max Activating Token Index: 18