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

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

Neuron 3205 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8920. Min Act: -0.0000

Data Index: 162515 (C4 (Web Text))

Max Activating Token Index: 261

Text #1

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.8772. Min Act: -0.0000

Data Index: 59563 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1050951 (C4 (Web Text))

Max Activating Token Index: 406

Text #3

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7097. Min Act: -0.0000

Data Index: 1291329 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6991. Min Act: -0.0000

Data Index: 20630 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7124. Min Act: -0.0000

Data Index: 151875 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6984. Min Act: -0.0000

Data Index: 85505 (C4 (Web Text))

Max Activating Token Index: 555

Text #7

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7343. Min Act: -0.0000

Data Index: 514415 (C4 (Web Text))

Max Activating Token Index: 731

Text #8

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.7083. Min Act: -0.0000

Data Index: 1211276 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6423. Min Act: -0.0000

Data Index: 462878 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6593. Min Act: -0.0000

Data Index: 1076046 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6785. Min Act: -0.0000

Data Index: 170987 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6333. Min Act: -0.0000

Data Index: 1279303 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6339. Min Act: -0.0000

Data Index: 1625931 (Python Code)

Max Activating Token Index: 96

Text #14

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6454. Min Act: -0.0000

Data Index: 938890 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1028686 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6361. Min Act: -0.0000

Data Index: 976249 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.6308. Min Act: -0.0000

Data Index: 1272174 (C4 (Web Text))

Max Activating Token Index: 924

Text #18

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.5746. Min Act: -0.0000

Data Index: 637943 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 0.8920. Min Range: -0.8920

Max Act: 0.5696. Min Act: -0.0000

Data Index: 629096 (C4 (Web Text))

Max Activating Token Index: 603