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

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

Neuron 2396 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.3269. Min Act: -0.0000

Data Index: 1087481 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1671. Min Act: -0.0000

Data Index: 761708 (C4 (Web Text))

Max Activating Token Index: 541

Text #2

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1243. Min Act: -0.0000

Data Index: 501256 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1461. Min Act: -0.0000

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.1675. Min Act: -0.0000

Data Index: 348868 (C4 (Web Text))

Max Activating Token Index: 115

Text #5

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1272484 (C4 (Web Text))

Max Activating Token Index: 305

Text #6

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0840. Min Act: -0.0000

Data Index: 183971 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0713. Min Act: -0.0000

Data Index: 712347 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0818. Min Act: -0.0000

Data Index: 815083 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 1.3269. Min Range: -1.3269

Max Act: 1.0401. Min Act: -0.0000

Data Index: 131736 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9676. Min Act: -0.0000

Data Index: 345970 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9654. Min Act: -0.0000

Data Index: 539332 (C4 (Web Text))

Max Activating Token Index: 207

Text #12

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8828. Min Act: -0.0000

Data Index: 849972 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1179325 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9176. Min Act: -0.0000

Data Index: 240577 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9153. Min Act: -0.0000

Data Index: 884621 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9468. Min Act: -0.0000

Data Index: 449001 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9400. Min Act: -0.0000

Data Index: 656239 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.8810. Min Act: -0.0000

Data Index: 1143136 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 1.3269. Min Range: -1.3269

Max Act: 0.9033. Min Act: -0.0000

Data Index: 585491 (C4 (Web Text))

Max Activating Token Index: 548