Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 391 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0488. Min Range: -1.0488

Max Act: 1.0488. Min Act: -0.0000

Data Index: 126697 (C4 (Web Text))

Max Activating Token Index: 218

Text #1

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.8748. Min Act: -0.0000

Data Index: 29565 (C4 (Web Text))

Max Activating Token Index: 62

Text #2

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.8175. Min Act: -0.0001

Data Index: 1052158 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.7891. Min Act: -0.0000

Data Index: 868446 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.7769. Min Act: -0.0000

Data Index: 364446 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.7330. Min Act: -0.0000

Data Index: 1251870 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.7316. Min Act: -0.0000

Data Index: 376576 (C4 (Web Text))

Max Activating Token Index: 149

Text #7

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6850. Min Act: -0.0000

Data Index: 149164 (C4 (Web Text))

Max Activating Token Index: 542

Text #8

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1027205 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6495. Min Act: -0.0000

Data Index: 581281 (C4 (Web Text))

Max Activating Token Index: 405

Text #10

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6409. Min Act: -0.0001

Data Index: 664840 (C4 (Web Text))

Max Activating Token Index: 289

Text #11

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6802. Min Act: -0.0001

Data Index: 768831 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.5773. Min Act: -0.0000

Data Index: 598132 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6128. Min Act: -0.0000

Data Index: 827674 (C4 (Web Text))

Max Activating Token Index: 852

Text #14

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1029295 (C4 (Web Text))

Max Activating Token Index: 214

Text #15

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6095. Min Act: -0.0000

Data Index: 56324 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1127020 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.6027. Min Act: -0.0001

Data Index: 300699 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.5897. Min Act: -0.0000

Data Index: 465948 (C4 (Web Text))

Max Activating Token Index: 789

Text #19

Max Range: 1.0488. Min Range: -1.0488

Max Act: 0.5840. Min Act: -0.0001

Data Index: 1169363 (C4 (Web Text))

Max Activating Token Index: 451