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

Dataset: The Pile

Neuron 580 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0032. Min Range: -1.0032

Max Act: 1.0032. Min Act: -0.0000

Data Index: 574404 (The Pile)

Max Activating Token Index: 655

Text #1

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.7311. Min Act: -0.0000

Data Index: 971406 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.7415. Min Act: -0.0000

Data Index: 1854363 (The Pile)

Max Activating Token Index: 492

Text #3

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1658131 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6872. Min Act: -0.0000

Data Index: 616394 (The Pile)

Max Activating Token Index: 452

Text #5

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.7068. Min Act: -0.0000

Data Index: 792099 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6325. Min Act: -0.0000

Data Index: 199964 (The Pile)

Max Activating Token Index: 389

Text #7

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6688. Min Act: -0.0000

Data Index: 1040088 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6864. Min Act: -0.0000

Data Index: 881557 (The Pile)

Max Activating Token Index: 959

Text #9

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6572. Min Act: -0.0000

Data Index: 676290 (The Pile)

Max Activating Token Index: 287

Text #10

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6356. Min Act: -0.0000

Data Index: 771511 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1067060 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6464. Min Act: -0.0000

Data Index: 410205 (The Pile)

Max Activating Token Index: 792

Text #13

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6230. Min Act: -0.0000

Data Index: 1718465 (The Pile)

Max Activating Token Index: 219

Text #14

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6162. Min Act: -0.0000

Data Index: 75963 (The Pile)

Max Activating Token Index: 487

Text #15

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1390934 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6491. Min Act: -0.0000

Data Index: 1946533 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.6236. Min Act: -0.0000

Data Index: 9011 (The Pile)

Max Activating Token Index: 512

Text #18

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.5945. Min Act: -0.0000

Data Index: 449305 (The Pile)

Max Activating Token Index: 51

Text #19

Max Range: 1.0032. Min Range: -1.0032

Max Act: 0.5697. Min Act: -0.0000

Data Index: 986393 (The Pile)

Max Activating Token Index: 132