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

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

Neuron 2651 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0392. Min Range: -3.0392

Max Act: 3.0392. Min Act: -0.0000

Data Index: 55359 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.9247. Min Act: -0.0000

Data Index: 728374 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.7804. Min Act: -0.0000

Data Index: 683489 (C4 (Web Text))

Max Activating Token Index: 207

Text #3

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.8515. Min Act: -0.0000

Data Index: 1014159 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.8446. Min Act: -0.0000

Data Index: 310091 (C4 (Web Text))

Max Activating Token Index: 744

Text #5

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.7114. Min Act: -0.0000

Data Index: 563019 (C4 (Web Text))

Max Activating Token Index: 836

Text #6

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.7048. Min Act: -0.0000

Data Index: 136673 (C4 (Web Text))

Max Activating Token Index: 463

Text #7

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.6241. Min Act: -0.0000

Data Index: 840940 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.6053. Min Act: -0.0000

Data Index: 399191 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.5979. Min Act: -0.0000

Data Index: 648817 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.5531. Min Act: -0.0000

Data Index: 553347 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.3389. Min Act: -0.0000

Data Index: 226361 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.4773. Min Act: -0.0000

Data Index: 1216615 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.3331. Min Act: -0.0000

Data Index: 553513 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.3012. Min Act: -0.0000

Data Index: 496661 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.4256. Min Act: -0.0000

Data Index: 150764 (C4 (Web Text))

Max Activating Token Index: 533

Text #16

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.4047. Min Act: -0.0000

Data Index: 1118673 (C4 (Web Text))

Max Activating Token Index: 130

Text #17

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.4084. Min Act: -0.0000

Data Index: 543034 (C4 (Web Text))

Max Activating Token Index: 946

Text #18

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.4081. Min Act: -0.0000

Data Index: 1184459 (C4 (Web Text))

Max Activating Token Index: 892

Text #19

Max Range: 3.0392. Min Range: -3.0392

Max Act: 2.2869. Min Act: -0.0000

Data Index: 461553 (C4 (Web Text))

Max Activating Token Index: 188