Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3960 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8938. Min Act: -0.0000

Data Index: 680929 (The Pile)

Max Activating Token Index: 982

Text #1

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9857. Min Act: -0.0000

Data Index: 1862880 (The Pile)

Max Activating Token Index: 171

Text #2

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.9237. Min Act: -0.0000

Data Index: 649777 (The Pile)

Max Activating Token Index: 901

Text #3

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8854. Min Act: -0.0000

Data Index: 438195 (The Pile)

Max Activating Token Index: 405

Text #4

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8275. Min Act: -0.0000

Data Index: 299861 (The Pile)

Max Activating Token Index: 782

Text #5

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7954. Min Act: -0.0000

Data Index: 390774 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1588923 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1148219 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7616. Min Act: -0.0000

Data Index: 996542 (The Pile)

Max Activating Token Index: 852

Text #9

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.8300. Min Act: -0.0000

Data Index: 1331107 (The Pile)

Max Activating Token Index: 990

Text #10

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1303072 (The Pile)

Max Activating Token Index: 986

Text #11

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7880. Min Act: -0.0000

Data Index: 813795 (The Pile)

Max Activating Token Index: 96

Text #12

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6910. Min Act: -0.0000

Data Index: 1232005 (The Pile)

Max Activating Token Index: 642

Text #13

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1351043 (The Pile)

Max Activating Token Index: 705

Text #14

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7031. Min Act: -0.0000

Data Index: 179681 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7151. Min Act: -0.0000

Data Index: 994768 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6684. Min Act: -0.0000

Data Index: 285498 (The Pile)

Max Activating Token Index: 500

Text #17

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7241. Min Act: -0.0000

Data Index: 531597 (The Pile)

Max Activating Token Index: 341

Text #18

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.7196. Min Act: -0.0000

Data Index: 1289938 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 0.9857. Min Range: -0.9857

Max Act: 0.6656. Min Act: -0.0000

Data Index: 737252 (The Pile)

Max Activating Token Index: 96