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

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

Neuron 1659 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5915. Min Act: -0.0001

Data Index: 580272 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.6172. Min Act: -0.0001

Data Index: 117112 (C4 (Web Text))

Max Activating Token Index: 493

Text #2

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5969. Min Act: -0.0001

Data Index: 1143263 (C4 (Web Text))

Max Activating Token Index: 420

Text #3

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.6108. Min Act: -0.0000

Data Index: 218157 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.6049. Min Act: -0.0001

Data Index: 950695 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5994. Min Act: -0.0001

Data Index: 239463 (C4 (Web Text))

Max Activating Token Index: 408

Text #6

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5783. Min Act: -0.0001

Data Index: 400192 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.6113. Min Act: -0.0001

Data Index: 1140469 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5838. Min Act: -0.0001

Data Index: 1248571 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5894. Min Act: -0.0001

Data Index: 1350737 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5642. Min Act: -0.0001

Data Index: 270512 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5743. Min Act: -0.0001

Data Index: 240334 (C4 (Web Text))

Max Activating Token Index: 377

Text #12

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5780. Min Act: -0.0001

Data Index: 792744 (C4 (Web Text))

Max Activating Token Index: 735

Text #13

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5749. Min Act: -0.0001

Data Index: 168695 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5837. Min Act: -0.0001

Data Index: 30586 (C4 (Web Text))

Max Activating Token Index: 965

Text #15

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5479. Min Act: -0.0001

Data Index: 1233362 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5482. Min Act: -0.0001

Data Index: 923221 (C4 (Web Text))

Max Activating Token Index: 508

Text #17

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5479. Min Act: -0.0001

Data Index: 1011297 (C4 (Web Text))

Max Activating Token Index: 374

Text #18

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5431. Min Act: -0.0001

Data Index: 227894 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.6172. Min Range: -0.6172

Max Act: 0.5588. Min Act: -0.0001

Data Index: 556475 (C4 (Web Text))

Max Activating Token Index: 520