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

Dataset: The Pile

Neuron 3533 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: 0.7201. Min Range: -0.7201

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1244992 (The Pile)

Max Activating Token Index: 720

Text #1

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1555931 (The Pile)

Max Activating Token Index: 590

Text #2

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6436. Min Act: -0.0000

Data Index: 1474067 (The Pile)

Max Activating Token Index: 146

Text #3

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6521. Min Act: -0.0000

Data Index: 126717 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1386579 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6292. Min Act: -0.0000

Data Index: 600678 (The Pile)

Max Activating Token Index: 417

Text #6

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6317. Min Act: -0.0000

Data Index: 365620 (The Pile)

Max Activating Token Index: 727

Text #7

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6445. Min Act: -0.0000

Data Index: 531643 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6254. Min Act: -0.0000

Data Index: 714908 (The Pile)

Max Activating Token Index: 546

Text #9

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6203. Min Act: -0.0000

Data Index: 1130812 (The Pile)

Max Activating Token Index: 477

Text #10

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5708. Min Act: -0.0000

Data Index: 504476 (The Pile)

Max Activating Token Index: 619

Text #11

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1339864 (The Pile)

Max Activating Token Index: 194

Text #12

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6194. Min Act: -0.0000

Data Index: 1235395 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6140. Min Act: 0.0000

Data Index: 1848624 (The Pile)

Max Activating Token Index: 896

Text #14

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5554. Min Act: 0.0000

Data Index: 863103 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.6102. Min Act: -0.0000

Data Index: 717768 (The Pile)

Max Activating Token Index: 846

Text #16

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5797. Min Act: -0.0000

Data Index: 518054 (The Pile)

Max Activating Token Index: 413

Text #17

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5621. Min Act: -0.0000

Data Index: 440669 (The Pile)

Max Activating Token Index: 376

Text #18

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1199047 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 0.7201. Min Range: -0.7201

Max Act: 0.5985. Min Act: -0.0000

Data Index: 535747 (The Pile)

Max Activating Token Index: 209