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

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

Neuron 4752 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1165495 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0849. Min Act: -0.0000

Data Index: 495852 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0811. Min Act: -0.0000

Data Index: 383859 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0873. Min Act: -0.0000

Data Index: 757772 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0897. Min Act: -0.0000

Data Index: 37593 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0832. Min Act: -0.0000

Data Index: 630700 (C4 (Web Text))

Max Activating Token Index: 929

Text #6

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0738. Min Act: -0.0000

Data Index: 1168072 (C4 (Web Text))

Max Activating Token Index: 930

Text #7

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1323406 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0743. Min Act: -0.0000

Data Index: 978737 (C4 (Web Text))

Max Activating Token Index: 979

Text #9

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0761. Min Act: -0.0000

Data Index: 495471 (C4 (Web Text))

Max Activating Token Index: 932

Text #10

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0702. Min Act: -0.0000

Data Index: 236596 (C4 (Web Text))

Max Activating Token Index: 973

Text #11

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0713. Min Act: -0.0000

Data Index: 1255179 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0700. Min Act: -0.0000

Data Index: 551783 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0724. Min Act: -0.0000

Data Index: 388579 (C4 (Web Text))

Max Activating Token Index: 729

Text #14

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0764. Min Act: -0.0000

Data Index: 40927 (C4 (Web Text))

Max Activating Token Index: 476

Text #15

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1028281 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0755. Min Act: -0.0000

Data Index: 58234 (C4 (Web Text))

Max Activating Token Index: 813

Text #17

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1130196 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0683. Min Act: -0.0000

Data Index: 112146 (C4 (Web Text))

Max Activating Token Index: 980

Text #19

Max Range: 0.0910. Min Range: -0.0910

Max Act: 0.0687. Min Act: -0.0000

Data Index: 776874 (C4 (Web Text))

Max Activating Token Index: 44