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

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

Neuron 4333 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1345. Min Act: -0.0002

Data Index: 23284 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1192. Min Act: -0.0001

Data Index: 704051 (C4 (Web Text))

Max Activating Token Index: 271

Text #2

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1127. Min Act: -0.0001

Data Index: 1033948 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1051. Min Act: -0.0001

Data Index: 689569 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1075. Min Act: -0.0002

Data Index: 700312 (C4 (Web Text))

Max Activating Token Index: 83

Text #5

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1301378 (C4 (Web Text))

Max Activating Token Index: 104

Text #6

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1029. Min Act: -0.0002

Data Index: 683605 (C4 (Web Text))

Max Activating Token Index: 120

Text #7

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.1007. Min Act: -0.0002

Data Index: 104171 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0988. Min Act: -0.0001

Data Index: 1278654 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0977. Min Act: -0.0002

Data Index: 577729 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0972. Min Act: -0.0002

Data Index: 665608 (C4 (Web Text))

Max Activating Token Index: 584

Text #11

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0953. Min Act: -0.0001

Data Index: 1190402 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0951. Min Act: -0.0001

Data Index: 52645 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0988. Min Act: -0.0002

Data Index: 321702 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0940. Min Act: -0.0001

Data Index: 389184 (C4 (Web Text))

Max Activating Token Index: 411

Text #15

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0903. Min Act: -0.0002

Data Index: 28797 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0935. Min Act: -0.0002

Data Index: 938323 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0969. Min Act: -0.0001

Data Index: 160070 (C4 (Web Text))

Max Activating Token Index: 336

Text #18

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1237028 (C4 (Web Text))

Max Activating Token Index: 964

Text #19

Max Range: 0.1345. Min Range: -0.1345

Max Act: 0.0963. Min Act: -0.0002

Data Index: 827416 (C4 (Web Text))

Max Activating Token Index: 983