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

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

Neuron 4167 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.8865. Min Range: -8.8865

Max Act: 8.8865. Min Act: -0.0000

Data Index: 374089 (C4 (Web Text))

Max Activating Token Index: 344

Text #1

Max Range: 8.8865. Min Range: -8.8865

Max Act: 7.8766. Min Act: -0.0000

Data Index: 246457 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 8.8865. Min Range: -8.8865

Max Act: 7.6449. Min Act: -0.0000

Data Index: 252069 (C4 (Web Text))

Max Activating Token Index: 992

Text #3

Max Range: 8.8865. Min Range: -8.8865

Max Act: 7.2704. Min Act: -0.0000

Data Index: 882919 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 8.8865. Min Range: -8.8865

Max Act: 7.3394. Min Act: -0.0000

Data Index: 1141052 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 8.8865. Min Range: -8.8865

Max Act: 7.3142. Min Act: -0.0000

Data Index: 518083 (C4 (Web Text))

Max Activating Token Index: 1006

Text #6

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.9346. Min Act: -0.0000

Data Index: 372906 (C4 (Web Text))

Max Activating Token Index: 698

Text #7

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.9728. Min Act: -0.0000

Data Index: 1282856 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.6723. Min Act: -0.0000

Data Index: 495185 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.3812. Min Act: -0.0000

Data Index: 1007805 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.3542. Min Act: -0.0000

Data Index: 682875 (C4 (Web Text))

Max Activating Token Index: 54

Text #11

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.2918. Min Act: -0.0000

Data Index: 226712 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.4086. Min Act: -0.0000

Data Index: 1321967 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.2873. Min Act: -0.0000

Data Index: 100178 (C4 (Web Text))

Max Activating Token Index: 954

Text #14

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.0981. Min Act: -0.0000

Data Index: 109096 (C4 (Web Text))

Max Activating Token Index: 206

Text #15

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.2730. Min Act: -0.0000

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.2743. Min Act: -0.0000

Data Index: 828426 (C4 (Web Text))

Max Activating Token Index: 967

Text #17

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.4343. Min Act: -0.0000

Data Index: 39619 (C4 (Web Text))

Max Activating Token Index: 799

Text #18

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.0085. Min Act: -0.0000

Data Index: 504050 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 8.8865. Min Range: -8.8865

Max Act: 6.1620. Min Act: -0.0000

Data Index: 1003948 (C4 (Web Text))

Max Activating Token Index: 710