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

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

Neuron 3770 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.3990. Min Act: -0.0000

Data Index: 1179306 (C4 (Web Text))

Max Activating Token Index: 49

Text #1

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.1075. Min Act: -0.0000

Data Index: 957406 (C4 (Web Text))

Max Activating Token Index: 560

Text #2

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0940. Min Act: -0.0000

Data Index: 83664 (C4 (Web Text))

Max Activating Token Index: 439

Text #3

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0169. Min Act: -0.0000

Data Index: 112148 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0084. Min Act: -0.0000

Data Index: 523757 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 1.3990. Min Range: -1.3990

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1215589 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9455. Min Act: 0.0000

Data Index: 1136609 (C4 (Web Text))

Max Activating Token Index: 533

Text #7

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.9173. Min Act: -0.0000

Data Index: 1264771 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8813. Min Act: -0.0000

Data Index: 50042 (C4 (Web Text))

Max Activating Token Index: 398

Text #9

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8782. Min Act: 0.0000

Data Index: 797283 (C4 (Web Text))

Max Activating Token Index: 987

Text #10

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8791. Min Act: -0.0000

Data Index: 604485 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8537. Min Act: -0.0000

Data Index: 315754 (C4 (Web Text))

Max Activating Token Index: 789

Text #12

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8573. Min Act: -0.0000

Data Index: 844348 (C4 (Web Text))

Max Activating Token Index: 24

Text #13

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8280. Min Act: 0.0000

Data Index: 52224 (C4 (Web Text))

Max Activating Token Index: 281

Text #14

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8219. Min Act: -0.0000

Data Index: 1040048 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1127110 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8236. Min Act: -0.0000

Data Index: 993982 (C4 (Web Text))

Max Activating Token Index: 843

Text #17

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8044. Min Act: 0.0000

Data Index: 391534 (C4 (Web Text))

Max Activating Token Index: 47

Text #18

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.8006. Min Act: 0.0000

Data Index: 1187275 (C4 (Web Text))

Max Activating Token Index: 88

Text #19

Max Range: 1.3990. Min Range: -1.3990

Max Act: 0.7639. Min Act: -0.0000

Data Index: 705246 (C4 (Web Text))

Max Activating Token Index: 131