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

Dataset: The Pile

Neuron 2400 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: 1.1223. Min Range: -1.1223

Max Act: 1.1223. Min Act: -0.0000

Data Index: 431500 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.9126. Min Act: -0.0000

Data Index: 166847 (The Pile)

Max Activating Token Index: 613

Text #2

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.8110. Min Act: -0.0000

Data Index: 1992539 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1071170 (The Pile)

Max Activating Token Index: 627

Text #4

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.7852. Min Act: -0.0000

Data Index: 907297 (The Pile)

Max Activating Token Index: 760

Text #5

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.7031. Min Act: -0.0000

Data Index: 156569 (The Pile)

Max Activating Token Index: 235

Text #6

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.7364. Min Act: -0.0000

Data Index: 867596 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.7098. Min Act: -0.0000

Data Index: 760541 (The Pile)

Max Activating Token Index: 735

Text #8

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6766. Min Act: -0.0000

Data Index: 795924 (The Pile)

Max Activating Token Index: 1002

Text #9

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1621741 (The Pile)

Max Activating Token Index: 602

Text #10

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6576. Min Act: -0.0000

Data Index: 141337 (The Pile)

Max Activating Token Index: 635

Text #11

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1659310 (The Pile)

Max Activating Token Index: 269

Text #12

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6314. Min Act: -0.0000

Data Index: 1361262 (The Pile)

Max Activating Token Index: 49

Text #13

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6084. Min Act: -0.0000

Data Index: 358148 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6591. Min Act: -0.0000

Data Index: 766411 (The Pile)

Max Activating Token Index: 601

Text #15

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6189. Min Act: -0.0000

Data Index: 906802 (The Pile)

Max Activating Token Index: 125

Text #16

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6038. Min Act: -0.0000

Data Index: 504301 (The Pile)

Max Activating Token Index: 399

Text #17

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6016. Min Act: -0.0000

Data Index: 537229 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.5992. Min Act: -0.0000

Data Index: 145115 (The Pile)

Max Activating Token Index: 156

Text #19

Max Range: 1.1223. Min Range: -1.1223

Max Act: 0.6136. Min Act: -0.0000

Data Index: 1069534 (The Pile)

Max Activating Token Index: 512