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

Dataset: The Pile

Neuron 2173 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: 4.1865. Min Range: -4.1865

Max Act: 3.8743. Min Act: 0.0000

Data Index: 757071 (The Pile)

Max Activating Token Index: 692

Text #1

Max Range: 4.1865. Min Range: -4.1865

Max Act: 4.1540. Min Act: -0.0000

Data Index: 267955 (The Pile)

Max Activating Token Index: 632

Text #2

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.9427. Min Act: -0.0000

Data Index: 240662 (The Pile)

Max Activating Token Index: 130

Text #3

Max Range: 4.1865. Min Range: -4.1865

Max Act: 4.1865. Min Act: -0.0000

Data Index: 1315922 (The Pile)

Max Activating Token Index: 509

Text #4

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.5230. Min Act: -0.0000

Data Index: 1289950 (The Pile)

Max Activating Token Index: 977

Text #5

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.5122. Min Act: -0.0000

Data Index: 632917 (The Pile)

Max Activating Token Index: 23

Text #6

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.6708. Min Act: -0.0000

Data Index: 419187 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.2593. Min Act: -0.0000

Data Index: 861376 (The Pile)

Max Activating Token Index: 190

Text #8

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.5406. Min Act: -0.0000

Data Index: 1615614 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.2171. Min Act: -0.0000

Data Index: 117651 (The Pile)

Max Activating Token Index: 288

Text #10

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.3412. Min Act: -0.0000

Data Index: 1977687 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.4712. Min Act: -0.0000

Data Index: 270067 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.3011. Min Act: -0.0000

Data Index: 352386 (The Pile)

Max Activating Token Index: 457

Text #13

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.2486. Min Act: -0.0000

Data Index: 883862 (The Pile)

Max Activating Token Index: 856

Text #14

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.2871. Min Act: -0.0000

Data Index: 816258 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.1011. Min Act: -0.0000

Data Index: 1973234 (The Pile)

Max Activating Token Index: 495

Text #16

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.2363. Min Act: -0.0000

Data Index: 1350525 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.4505. Min Act: -0.0000

Data Index: 1924323 (The Pile)

Max Activating Token Index: 209

Text #18

Max Range: 4.1865. Min Range: -4.1865

Max Act: 3.1305. Min Act: -0.0000

Data Index: 1267352 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 4.1865. Min Range: -4.1865

Max Act: 2.8257. Min Act: -0.0000

Data Index: 399107 (The Pile)

Max Activating Token Index: 56