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

Dataset: The Pile

Neuron 4809 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.3125. Min Act: -0.0000

Data Index: 1290029 (The Pile)

Max Activating Token Index: 158

Text #1

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.1533. Min Act: -0.0000

Data Index: 1163830 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.2259. Min Act: -0.0000

Data Index: 1148559 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.1537. Min Act: -0.0000

Data Index: 1729677 (The Pile)

Max Activating Token Index: 739

Text #4

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.2111. Min Act: -0.0000

Data Index: 637448 (The Pile)

Max Activating Token Index: 359

Text #5

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.1364. Min Act: -0.0000

Data Index: 13984 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1273983 (The Pile)

Max Activating Token Index: 950

Text #7

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.0700. Min Act: -0.0000

Data Index: 1398516 (The Pile)

Max Activating Token Index: 984

Text #8

Max Range: 1.3125. Min Range: -1.3125

Max Act: 0.9870. Min Act: -0.0000

Data Index: 1301809 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.0722. Min Act: -0.0000

Data Index: 907934 (The Pile)

Max Activating Token Index: 898

Text #10

Max Range: 1.3125. Min Range: -1.3125

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1744471 (The Pile)

Max Activating Token Index: 809

Text #11

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.0607. Min Act: -0.0000

Data Index: 1926966 (The Pile)

Max Activating Token Index: 505

Text #12

Max Range: 1.3125. Min Range: -1.3125

Max Act: 0.9887. Min Act: -0.0000

Data Index: 724718 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1811971 (The Pile)

Max Activating Token Index: 768

Text #14

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.0216. Min Act: -0.0000

Data Index: 1468330 (The Pile)

Max Activating Token Index: 184

Text #15

Max Range: 1.3125. Min Range: -1.3125

Max Act: 0.9443. Min Act: -0.0000

Data Index: 26887 (The Pile)

Max Activating Token Index: 562

Text #16

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1127369 (The Pile)

Max Activating Token Index: 996

Text #17

Max Range: 1.3125. Min Range: -1.3125

Max Act: 0.9588. Min Act: -0.0000

Data Index: 876612 (The Pile)

Max Activating Token Index: 196

Text #18

Max Range: 1.3125. Min Range: -1.3125

Max Act: 0.9028. Min Act: -0.0000

Data Index: 984333 (The Pile)

Max Activating Token Index: 91

Text #19

Max Range: 1.3125. Min Range: -1.3125

Max Act: 1.0099. Min Act: -0.0000

Data Index: 487573 (The Pile)

Max Activating Token Index: 651