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

Dataset: The Pile

Neuron 2049 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1789. Min Range: -1.1789

Max Act: 1.1163. Min Act: -0.0000

Data Index: 1375627 (The Pile)

Max Activating Token Index: 622

Text #1

Max Range: 1.1789. Min Range: -1.1789

Max Act: 1.1789. Min Act: -0.0000

Data Index: 1388875 (The Pile)

Max Activating Token Index: 783

Text #2

Max Range: 1.1789. Min Range: -1.1789

Max Act: 1.0329. Min Act: -0.0000

Data Index: 756037 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 1.1789. Min Range: -1.1789

Max Act: 1.0008. Min Act: -0.0000

Data Index: 795998 (The Pile)

Max Activating Token Index: 284

Text #4

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8983. Min Act: -0.0000

Data Index: 405370 (The Pile)

Max Activating Token Index: 76

Text #5

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9457. Min Act: -0.0000

Data Index: 1544837 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 1.1789. Min Range: -1.1789

Max Act: 1.0449. Min Act: -0.0000

Data Index: 1446642 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1352240 (The Pile)

Max Activating Token Index: 263

Text #8

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9445. Min Act: -0.0000

Data Index: 280527 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8540. Min Act: -0.0000

Data Index: 1019784 (The Pile)

Max Activating Token Index: 981

Text #10

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1429921 (The Pile)

Max Activating Token Index: 254

Text #11

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9556. Min Act: -0.0000

Data Index: 1224369 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8577. Min Act: -0.0000

Data Index: 1997915 (The Pile)

Max Activating Token Index: 53

Text #13

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1409803 (The Pile)

Max Activating Token Index: 36

Text #14

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.7868. Min Act: -0.0000

Data Index: 1305272 (The Pile)

Max Activating Token Index: 665

Text #15

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8672. Min Act: -0.0000

Data Index: 79841 (The Pile)

Max Activating Token Index: 257

Text #16

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1509871 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1858764 (The Pile)

Max Activating Token Index: 237

Text #18

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.8439. Min Act: -0.0000

Data Index: 707197 (The Pile)

Max Activating Token Index: 322

Text #19

Max Range: 1.1789. Min Range: -1.1789

Max Act: 0.9012. Min Act: -0.0000

Data Index: 977516 (The Pile)

Max Activating Token Index: 71