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

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

Neuron 729 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1252777 (C4 (Web Text))

Max Activating Token Index: 652

Text #1

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0753. Min Act: -0.0001

Data Index: 519212 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0771. Min Act: -0.0001

Data Index: 1113188 (C4 (Web Text))

Max Activating Token Index: 125

Text #3

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0734. Min Act: -0.0001

Data Index: 689293 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0728. Min Act: -0.0001

Data Index: 487061 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0727. Min Act: -0.0001

Data Index: 158849 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0712. Min Act: -0.0001

Data Index: 617243 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0689. Min Act: -0.0001

Data Index: 79257 (C4 (Web Text))

Max Activating Token Index: 43

Text #8

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0630. Min Act: -0.0001

Data Index: 387800 (C4 (Web Text))

Max Activating Token Index: 285

Text #9

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0657. Min Act: -0.0001

Data Index: 619767 (C4 (Web Text))

Max Activating Token Index: 454

Text #10

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0669. Min Act: -0.0001

Data Index: 1199125 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0665. Min Act: -0.0001

Data Index: 389413 (C4 (Web Text))

Max Activating Token Index: 748

Text #12

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1195307 (C4 (Web Text))

Max Activating Token Index: 474

Text #13

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0643. Min Act: -0.0001

Data Index: 12740 (C4 (Web Text))

Max Activating Token Index: 465

Text #14

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0591. Min Act: -0.0001

Data Index: 165921 (C4 (Web Text))

Max Activating Token Index: 301

Text #15

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0610. Min Act: -0.0001

Data Index: 994211 (C4 (Web Text))

Max Activating Token Index: 561

Text #16

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1615140 (Python Code)

Max Activating Token Index: 125

Text #17

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0637. Min Act: -0.0001

Data Index: 183637 (C4 (Web Text))

Max Activating Token Index: 125

Text #18

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1200822 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.0869. Min Range: -0.0869

Max Act: 0.0618. Min Act: -0.0001

Data Index: 567613 (C4 (Web Text))

Max Activating Token Index: 114