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

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

Neuron 4419 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.6394. Min Act: -0.0000

Data Index: 236605 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.4748. Min Act: -0.0000

Data Index: 886226 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.2476. Min Act: -0.0000

Data Index: 1114395 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.2603. Min Act: -0.0000

Data Index: 561575 (C4 (Web Text))

Max Activating Token Index: 1003

Text #4

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.1362. Min Act: -0.0000

Data Index: 991839 (C4 (Web Text))

Max Activating Token Index: 814

Text #5

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0907. Min Act: -0.0000

Data Index: 1534601 (Python Code)

Max Activating Token Index: 829

Text #6

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.1158. Min Act: -0.0000

Data Index: 579227 (C4 (Web Text))

Max Activating Token Index: 238

Text #7

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0577. Min Act: -0.0000

Data Index: 709105 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1355245 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 1.6394. Min Range: -1.6394

Max Act: 0.8900. Min Act: -0.0000

Data Index: 232909 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0898. Min Act: -0.0000

Data Index: 852311 (C4 (Web Text))

Max Activating Token Index: 538

Text #11

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0129. Min Act: -0.0000

Data Index: 1478447 (Python Code)

Max Activating Token Index: 578

Text #12

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0681. Min Act: -0.0000

Data Index: 52144 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0899. Min Act: -0.0000

Data Index: 82369 (C4 (Web Text))

Max Activating Token Index: 879

Text #14

Max Range: 1.6394. Min Range: -1.6394

Max Act: 0.9919. Min Act: -0.0000

Data Index: 761924 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 1.6394. Min Range: -1.6394

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1234370 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 1.6394. Min Range: -1.6394

Max Act: 0.9792. Min Act: -0.0000

Data Index: 1103999 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 1.6394. Min Range: -1.6394

Max Act: 0.9704. Min Act: -0.0000

Data Index: 1217500 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 1.6394. Min Range: -1.6394

Max Act: 0.9640. Min Act: -0.0000

Data Index: 687233 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 1.6394. Min Range: -1.6394

Max Act: 0.9608. Min Act: -0.0000

Data Index: 152832 (C4 (Web Text))

Max Activating Token Index: 756