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

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

Neuron 6091 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.1365. Min Act: 0.0000

Data Index: 234217 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0926. Min Act: 0.0000

Data Index: 1203660 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0865. Min Act: -0.0000

Data Index: 1631627 (Python Code)

Max Activating Token Index: 145

Text #3

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1553084 (Python Code)

Max Activating Token Index: 184

Text #4

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0802. Min Act: -0.0000

Data Index: 885372 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0823. Min Act: -0.0000

Data Index: 1162582 (C4 (Web Text))

Max Activating Token Index: 812

Text #6

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0735. Min Act: -0.0000

Data Index: 667560 (C4 (Web Text))

Max Activating Token Index: 619

Text #7

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0767. Min Act: 0.0000

Data Index: 628894 (C4 (Web Text))

Max Activating Token Index: 185

Text #8

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1332429 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0761. Min Act: -0.0000

Data Index: 662750 (C4 (Web Text))

Max Activating Token Index: 163

Text #10

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0717. Min Act: -0.0000

Data Index: 300966 (C4 (Web Text))

Max Activating Token Index: 480

Text #11

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1375217 (Python Code)

Max Activating Token Index: 927

Text #12

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0722. Min Act: -0.0000

Data Index: 585556 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0719. Min Act: -0.0000

Data Index: 974310 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1550675 (Python Code)

Max Activating Token Index: 966

Text #15

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1481794 (Python Code)

Max Activating Token Index: 125

Text #16

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0713. Min Act: -0.0000

Data Index: 324921 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0712. Min Act: -0.0000

Data Index: 1539727 (Python Code)

Max Activating Token Index: 355

Text #18

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0674. Min Act: -0.0000

Data Index: 550121 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.1365. Min Range: -0.1365

Max Act: 0.0689. Min Act: -0.0000

Data Index: 630713 (C4 (Web Text))

Max Activating Token Index: 766