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

Dataset: The Pile

Neuron 4014 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7931. Min Act: -0.0000

Data Index: 40302 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9096. Min Act: -0.0000

Data Index: 1181601 (The Pile)

Max Activating Token Index: 630

Text #2

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8418. Min Act: -0.0000

Data Index: 494460 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1036824 (The Pile)

Max Activating Token Index: 14

Text #4

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.9418. Min Act: -0.0000

Data Index: 112721 (The Pile)

Max Activating Token Index: 361

Text #5

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8731. Min Act: -0.0000

Data Index: 1451478 (The Pile)

Max Activating Token Index: 360

Text #6

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8852. Min Act: -0.0000

Data Index: 1287038 (The Pile)

Max Activating Token Index: 37

Text #7

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8524. Min Act: -0.0000

Data Index: 1857330 (The Pile)

Max Activating Token Index: 892

Text #8

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7436. Min Act: -0.0000

Data Index: 1654294 (The Pile)

Max Activating Token Index: 90

Text #9

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8211. Min Act: -0.0000

Data Index: 265316 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8148. Min Act: -0.0000

Data Index: 6984 (The Pile)

Max Activating Token Index: 509

Text #11

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7586. Min Act: -0.0000

Data Index: 1973589 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7859. Min Act: -0.0000

Data Index: 472847 (The Pile)

Max Activating Token Index: 165

Text #13

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.8269. Min Act: -0.0000

Data Index: 1688668 (The Pile)

Max Activating Token Index: 87

Text #14

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7271. Min Act: -0.0000

Data Index: 961228 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7435. Min Act: -0.0000

Data Index: 41312 (The Pile)

Max Activating Token Index: 477

Text #16

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7652. Min Act: -0.0000

Data Index: 972574 (The Pile)

Max Activating Token Index: 561

Text #17

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7362. Min Act: -0.0000

Data Index: 1549932 (The Pile)

Max Activating Token Index: 214

Text #18

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7133. Min Act: -0.0000

Data Index: 816939 (The Pile)

Max Activating Token Index: 312

Text #19

Max Range: 0.9418. Min Range: -0.9418

Max Act: 0.7005. Min Act: -0.0000

Data Index: 531431 (The Pile)

Max Activating Token Index: 935