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

Dataset: The Pile

Neuron 3113 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.8505. Min Range: -4.8505

Max Act: 4.8505. Min Act: -0.0000

Data Index: 667421 (The Pile)

Max Activating Token Index: 514

Text #1

Max Range: 4.8505. Min Range: -4.8505

Max Act: 4.1568. Min Act: -0.0000

Data Index: 1749265 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 4.8505. Min Range: -4.8505

Max Act: 4.0437. Min Act: -0.0000

Data Index: 1402903 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 4.8505. Min Range: -4.8505

Max Act: 4.0413. Min Act: -0.0000

Data Index: 1540211 (The Pile)

Max Activating Token Index: 525

Text #4

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.9800. Min Act: -0.0000

Data Index: 1318752 (The Pile)

Max Activating Token Index: 892

Text #5

Max Range: 4.8505. Min Range: -4.8505

Max Act: 4.0668. Min Act: -0.0000

Data Index: 538426 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.9889. Min Act: -0.0000

Data Index: 1455627 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.9800. Min Act: -0.0000

Data Index: 662493 (The Pile)

Max Activating Token Index: 955

Text #8

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.7531. Min Act: -0.0000

Data Index: 160972 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.4476. Min Act: -0.0000

Data Index: 1922088 (The Pile)

Max Activating Token Index: 723

Text #10

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.5457. Min Act: -0.0000

Data Index: 1247424 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.4142. Min Act: -0.0000

Data Index: 289286 (The Pile)

Max Activating Token Index: 333

Text #12

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.8382. Min Act: -0.0000

Data Index: 722419 (The Pile)

Max Activating Token Index: 703

Text #13

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.5068. Min Act: -0.0000

Data Index: 959984 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.6765. Min Act: -0.0000

Data Index: 1854834 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.6754. Min Act: -0.0000

Data Index: 1632805 (The Pile)

Max Activating Token Index: 318

Text #16

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.1406. Min Act: -0.0000

Data Index: 829592 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.6566. Min Act: -0.0000

Data Index: 1897003 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.4639. Min Act: -0.0000

Data Index: 814865 (The Pile)

Max Activating Token Index: 215

Text #19

Max Range: 4.8505. Min Range: -4.8505

Max Act: 3.4307. Min Act: -0.0000

Data Index: 436040 (The Pile)

Max Activating Token Index: 596