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

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

Neuron 2279 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: 0.9928. Min Range: -0.9928

Max Act: 0.9928. Min Act: -0.0000

Data Index: 1252684 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8993. Min Act: -0.0000

Data Index: 1032415 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8368. Min Act: -0.0001

Data Index: 517310 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8071. Min Act: -0.0000

Data Index: 1070152 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7990. Min Act: -0.0001

Data Index: 1072610 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8216. Min Act: -0.0000

Data Index: 100774 (C4 (Web Text))

Max Activating Token Index: 964

Text #6

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8098. Min Act: -0.0000

Data Index: 20910 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1118881 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8015. Min Act: -0.0000

Data Index: 149832 (C4 (Web Text))

Max Activating Token Index: 478

Text #9

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7214. Min Act: -0.0000

Data Index: 292871 (C4 (Web Text))

Max Activating Token Index: 59

Text #10

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.8233. Min Act: -0.0000

Data Index: 1050107 (C4 (Web Text))

Max Activating Token Index: 167

Text #11

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7487. Min Act: -0.0000

Data Index: 537362 (C4 (Web Text))

Max Activating Token Index: 231

Text #12

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7735. Min Act: -0.0000

Data Index: 123079 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7481. Min Act: -0.0000

Data Index: 279427 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7370. Min Act: -0.0000

Data Index: 1033709 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1251335 (C4 (Web Text))

Max Activating Token Index: 831

Text #16

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7043. Min Act: -0.0000

Data Index: 1298938 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.6852. Min Act: -0.0000

Data Index: 506094 (C4 (Web Text))

Max Activating Token Index: 40

Text #18

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1302536 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 0.9928. Min Range: -0.9928

Max Act: 0.7033. Min Act: -0.0001

Data Index: 766778 (C4 (Web Text))

Max Activating Token Index: 710