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

Dataset: The Pile

Neuron 1699 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.7007. Min Act: -0.0000

Data Index: 384392 (The Pile)

Max Activating Token Index: 97

Text #1

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.6525. Min Act: -0.0000

Data Index: 445204 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5784. Min Act: -0.0000

Data Index: 465132 (The Pile)

Max Activating Token Index: 917

Text #3

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1377961 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1107048 (The Pile)

Max Activating Token Index: 885

Text #5

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5403. Min Act: -0.0000

Data Index: 876139 (The Pile)

Max Activating Token Index: 62

Text #6

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5292. Min Act: -0.0000

Data Index: 641729 (The Pile)

Max Activating Token Index: 136

Text #7

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1590918 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5709. Min Act: -0.0000

Data Index: 79014 (The Pile)

Max Activating Token Index: 698

Text #9

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1120120 (The Pile)

Max Activating Token Index: 575

Text #10

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5156. Min Act: 0.0000

Data Index: 1117337 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5482. Min Act: -0.0000

Data Index: 550242 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5473. Min Act: -0.0000

Data Index: 954138 (The Pile)

Max Activating Token Index: 770

Text #13

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5048. Min Act: -0.0000

Data Index: 1286351 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1718722 (The Pile)

Max Activating Token Index: 528

Text #15

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1847819 (The Pile)

Max Activating Token Index: 1017

Text #16

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5210. Min Act: -0.0000

Data Index: 646000 (The Pile)

Max Activating Token Index: 975

Text #17

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.4858. Min Act: -0.0000

Data Index: 393086 (The Pile)

Max Activating Token Index: 124

Text #18

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1867870 (The Pile)

Max Activating Token Index: 177

Text #19

Max Range: 0.7007. Min Range: -0.7007

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1092973 (The Pile)

Max Activating Token Index: 630