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

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

Neuron 2984 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.7634. Min Act: -0.0000

Data Index: 829957 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.3907. Min Act: -0.0000

Data Index: 452793 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.4117. Min Act: -0.0000

Data Index: 371521 (C4 (Web Text))

Max Activating Token Index: 675

Text #3

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.5053. Min Act: -0.0000

Data Index: 637850 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.3212. Min Act: -0.0000

Data Index: 444300 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.1481. Min Act: -0.0000

Data Index: 786824 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.1086. Min Act: -0.0000

Data Index: 216300 (C4 (Web Text))

Max Activating Token Index: 341

Text #7

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.3493. Min Act: -0.0000

Data Index: 1101236 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.2928. Min Act: -0.0000

Data Index: 856213 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.0531. Min Act: -0.0000

Data Index: 640653 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.2564. Min Act: -0.0000

Data Index: 426881 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 2.7634. Min Range: -2.7634

Max Act: 1.9016. Min Act: -0.0000

Data Index: 839959 (C4 (Web Text))

Max Activating Token Index: 941

Text #12

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.1147. Min Act: -0.0000

Data Index: 572082 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.0415. Min Act: -0.0000

Data Index: 471333 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.0553. Min Act: -0.0000

Data Index: 732463 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.1722. Min Act: -0.0000

Data Index: 1012079 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.1547. Min Act: -0.0000

Data Index: 1045176 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 2.7634. Min Range: -2.7634

Max Act: 2.0216. Min Act: -0.0000

Data Index: 338491 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 2.7634. Min Range: -2.7634

Max Act: 1.9021. Min Act: -0.0000

Data Index: 1064439 (C4 (Web Text))

Max Activating Token Index: 992

Text #19

Max Range: 2.7634. Min Range: -2.7634

Max Act: 1.9843. Min Act: -0.0000

Data Index: 288621 (C4 (Web Text))

Max Activating Token Index: 11