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

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

Neuron 1743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.4253. Min Act: -0.0000

Data Index: 841307 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.5891. Min Act: -0.0000

Data Index: 309822 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.3479. Min Act: -0.0000

Data Index: 346449 (C4 (Web Text))

Max Activating Token Index: 131

Text #3

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.0581. Min Act: -0.0000

Data Index: 43196 (C4 (Web Text))

Max Activating Token Index: 55

Text #4

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.0672. Min Act: -0.0000

Data Index: 8708 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.1479. Min Act: -0.0000

Data Index: 730585 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.1511. Min Act: -0.0000

Data Index: 88262 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.1128. Min Act: -0.0000

Data Index: 706837 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.1113. Min Act: -0.0000

Data Index: 1079960 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.1050. Min Act: -0.0000

Data Index: 762128 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.2539. Min Act: -0.0000

Data Index: 1008921 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 2.5891. Min Range: -2.5891

Max Act: 1.9216. Min Act: -0.0000

Data Index: 951052 (C4 (Web Text))

Max Activating Token Index: 677

Text #12

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.1438. Min Act: -0.0000

Data Index: 669555 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.1087. Min Act: -0.0000

Data Index: 13449 (C4 (Web Text))

Max Activating Token Index: 903

Text #14

Max Range: 2.5891. Min Range: -2.5891

Max Act: 1.9567. Min Act: -0.0000

Data Index: 1251653 (C4 (Web Text))

Max Activating Token Index: 507

Text #15

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.0527. Min Act: -0.0001

Data Index: 1444998 (Python Code)

Max Activating Token Index: 742

Text #16

Max Range: 2.5891. Min Range: -2.5891

Max Act: 2.0365. Min Act: -0.0000

Data Index: 387251 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 2.5891. Min Range: -2.5891

Max Act: 1.8051. Min Act: -0.0000

Data Index: 80547 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 2.5891. Min Range: -2.5891

Max Act: 1.9137. Min Act: -0.0000

Data Index: 730639 (C4 (Web Text))

Max Activating Token Index: 603

Text #19

Max Range: 2.5891. Min Range: -2.5891

Max Act: 1.9832. Min Act: -0.0000

Data Index: 753729 (C4 (Web Text))

Max Activating Token Index: 640