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

Dataset: The Pile

Neuron 4821 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: 1.0477. Min Range: -1.0477

Max Act: 1.0477. Min Act: -0.0000

Data Index: 1186097 (The Pile)

Max Activating Token Index: 190

Text #1

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7982. Min Act: -0.0000

Data Index: 46042 (The Pile)

Max Activating Token Index: 755

Text #2

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7615. Min Act: -0.0000

Data Index: 313569 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.8077. Min Act: -0.0000

Data Index: 1843705 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7456. Min Act: -0.0000

Data Index: 577028 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7395. Min Act: -0.0000

Data Index: 978851 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7351. Min Act: -0.0000

Data Index: 601803 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1841508 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6635. Min Act: -0.0000

Data Index: 1042476 (The Pile)

Max Activating Token Index: 242

Text #9

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7339. Min Act: -0.0000

Data Index: 1864363 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6874. Min Act: -0.0000

Data Index: 511390 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6891. Min Act: -0.0000

Data Index: 1005299 (The Pile)

Max Activating Token Index: 320

Text #12

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7277. Min Act: -0.0000

Data Index: 1782787 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1214607 (The Pile)

Max Activating Token Index: 52

Text #14

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1702734 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1471839 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1754888 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6484. Min Act: -0.0000

Data Index: 949271 (The Pile)

Max Activating Token Index: 165

Text #18

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6721. Min Act: -0.0000

Data Index: 456727 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 1.0477. Min Range: -1.0477

Max Act: 0.6411. Min Act: -0.0000

Data Index: 87115 (The Pile)

Max Activating Token Index: 736