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

Dataset: The Pile

Neuron 3701 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.1987. Min Act: -0.0000

Data Index: 220951 (The Pile)

Max Activating Token Index: 324

Text #1

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.2745. Min Act: -0.0000

Data Index: 311575 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.1291. Min Act: -0.0000

Data Index: 278782 (The Pile)

Max Activating Token Index: 228

Text #3

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0946. Min Act: -0.0000

Data Index: 1504585 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1305037 (The Pile)

Max Activating Token Index: 855

Text #5

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0921. Min Act: -0.0000

Data Index: 327835 (The Pile)

Max Activating Token Index: 86

Text #6

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.1145. Min Act: -0.0000

Data Index: 539301 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1142540 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0539. Min Act: -0.0000

Data Index: 830981 (The Pile)

Max Activating Token Index: 576

Text #9

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1456248 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9953. Min Act: -0.0000

Data Index: 1224240 (The Pile)

Max Activating Token Index: 8

Text #11

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1352960 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9740. Min Act: -0.0000

Data Index: 770839 (The Pile)

Max Activating Token Index: 260

Text #13

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1253097 (The Pile)

Max Activating Token Index: 631

Text #14

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9671. Min Act: -0.0000

Data Index: 1723954 (The Pile)

Max Activating Token Index: 431

Text #15

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9346. Min Act: -0.0000

Data Index: 1528497 (The Pile)

Max Activating Token Index: 343

Text #16

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1353168 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9303. Min Act: -0.0000

Data Index: 130937 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9971. Min Act: -0.0000

Data Index: 1751366 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9022. Min Act: -0.0000

Data Index: 391542 (The Pile)

Max Activating Token Index: 34