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

Dataset: The Pile

Neuron 413 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.3639. Min Act: -0.0000

Data Index: 338896 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.6175. Min Act: -0.0000

Data Index: 1652673 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.8306. Min Act: -0.0000

Data Index: 1641946 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.0001. Min Act: -0.0000

Data Index: 66410 (The Pile)

Max Activating Token Index: 683

Text #4

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.0117. Min Act: -0.0000

Data Index: 468402 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.0763. Min Act: -0.0000

Data Index: 1572960 (The Pile)

Max Activating Token Index: 532

Text #6

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.2156. Min Act: -0.0000

Data Index: 915834 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.8621. Min Act: -0.0000

Data Index: 451517 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.0218. Min Act: -0.0000

Data Index: 598815 (The Pile)

Max Activating Token Index: 639

Text #9

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.6742. Min Act: -0.0000

Data Index: 1648503 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.6676. Min Act: -0.0000

Data Index: 1748004 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.0246. Min Act: -0.0000

Data Index: 313316 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.0360. Min Act: -0.0000

Data Index: 997004 (The Pile)

Max Activating Token Index: 745

Text #13

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.2058. Min Act: -0.0000

Data Index: 240174 (The Pile)

Max Activating Token Index: 674

Text #14

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.8090. Min Act: -0.0000

Data Index: 1318774 (The Pile)

Max Activating Token Index: 817

Text #15

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.6806. Min Act: -0.0000

Data Index: 917334 (The Pile)

Max Activating Token Index: 724

Text #16

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.4221. Min Act: -0.0000

Data Index: 208422 (The Pile)

Max Activating Token Index: 558

Text #17

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.5030. Min Act: -0.0000

Data Index: 1424225 (The Pile)

Max Activating Token Index: 715

Text #18

Max Range: 5.6175. Min Range: -5.6175

Max Act: 4.6803. Min Act: -0.0000

Data Index: 1205612 (The Pile)

Max Activating Token Index: 745

Text #19

Max Range: 5.6175. Min Range: -5.6175

Max Act: 5.1969. Min Act: -0.0000

Data Index: 1818285 (The Pile)

Max Activating Token Index: 749