Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3315 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.8469. Min Act: -0.0000

Data Index: 419606 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.8461. Min Act: -0.0000

Data Index: 1322076 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.8909. Min Act: -0.0000

Data Index: 1102577 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.8116. Min Act: -0.0000

Data Index: 1132261 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.7713. Min Act: -0.0000

Data Index: 59123 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.7509. Min Act: -0.0000

Data Index: 54013 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.7262. Min Act: -0.0000

Data Index: 67535 (C4 (Web Text))

Max Activating Token Index: 231

Text #7

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.7055. Min Act: -0.0000

Data Index: 582053 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.6017. Min Act: -0.0000

Data Index: 291815 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1218754 (C4 (Web Text))

Max Activating Token Index: 759

Text #10

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.7130. Min Act: -0.0000

Data Index: 512495 (C4 (Web Text))

Max Activating Token Index: 223

Text #11

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.6037. Min Act: -0.0000

Data Index: 386084 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.6030. Min Act: -0.0000

Data Index: 1356152 (C4 (Web Text))

Max Activating Token Index: 810

Text #13

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.5706. Min Act: -0.0000

Data Index: 277700 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.4678. Min Act: -0.0000

Data Index: 466462 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.5279. Min Act: -0.0000

Data Index: 140014 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.4406. Min Act: -0.0000

Data Index: 256543 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.5123. Min Act: -0.0000

Data Index: 581385 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.5073. Min Act: -0.0000

Data Index: 650017 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.8909. Min Range: -1.8909

Max Act: 1.4988. Min Act: -0.0000

Data Index: 137370 (C4 (Web Text))

Max Activating Token Index: 280