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

Dataset: The Pile

Neuron 2560 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.5559. Min Act: -0.0000

Data Index: 66349 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.6817. Min Act: -0.0000

Data Index: 813203 (The Pile)

Max Activating Token Index: 539

Text #2

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.6834. Min Act: -0.0000

Data Index: 1303324 (The Pile)

Max Activating Token Index: 436

Text #3

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.7944. Min Act: -0.0000

Data Index: 1340207 (The Pile)

Max Activating Token Index: 423

Text #4

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.6284. Min Act: -0.0000

Data Index: 1382633 (The Pile)

Max Activating Token Index: 868

Text #5

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.4435. Min Act: -0.0000

Data Index: 341495 (The Pile)

Max Activating Token Index: 430

Text #6

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.5594. Min Act: -0.0000

Data Index: 1207871 (The Pile)

Max Activating Token Index: 244

Text #7

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.5526. Min Act: -0.0000

Data Index: 1512795 (The Pile)

Max Activating Token Index: 203

Text #8

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.3896. Min Act: -0.0000

Data Index: 1285651 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.5516. Min Act: -0.0000

Data Index: 937730 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.2077. Min Act: -0.0000

Data Index: 798801 (The Pile)

Max Activating Token Index: 366

Text #11

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.4865. Min Act: -0.0000

Data Index: 792501 (The Pile)

Max Activating Token Index: 530

Text #12

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.4267. Min Act: -0.0000

Data Index: 1679947 (The Pile)

Max Activating Token Index: 532

Text #13

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.5139. Min Act: -0.0000

Data Index: 1522198 (The Pile)

Max Activating Token Index: 221

Text #14

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.3920. Min Act: -0.0000

Data Index: 913782 (The Pile)

Max Activating Token Index: 532

Text #15

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.3840. Min Act: -0.0000

Data Index: 936409 (The Pile)

Max Activating Token Index: 566

Text #16

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.3818. Min Act: -0.0000

Data Index: 645634 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.2031. Min Act: -0.0000

Data Index: 1035058 (The Pile)

Max Activating Token Index: 54

Text #18

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.3556. Min Act: -0.0000

Data Index: 171168 (The Pile)

Max Activating Token Index: 765

Text #19

Max Range: 3.7944. Min Range: -3.7944

Max Act: 3.6765. Min Act: -0.0000

Data Index: 1512625 (The Pile)

Max Activating Token Index: 263