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

Dataset: The Pile

Neuron 2853 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: 5.0668. Min Range: -5.0668

Max Act: 5.0668. Min Act: -0.0000

Data Index: 1382968 (The Pile)

Max Activating Token Index: 997

Text #1

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.6626. Min Act: -0.0000

Data Index: 450148 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.6534. Min Act: -0.0000

Data Index: 610810 (The Pile)

Max Activating Token Index: 949

Text #3

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.7043. Min Act: -0.0000

Data Index: 522097 (The Pile)

Max Activating Token Index: 962

Text #4

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.3247. Min Act: -0.0000

Data Index: 587898 (The Pile)

Max Activating Token Index: 486

Text #5

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.6414. Min Act: -0.0000

Data Index: 1885402 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.3459. Min Act: -0.0000

Data Index: 1954350 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.3254. Min Act: -0.0000

Data Index: 1999805 (The Pile)

Max Activating Token Index: 566

Text #8

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1456. Min Act: -0.0000

Data Index: 1390967 (The Pile)

Max Activating Token Index: 412

Text #9

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2657. Min Act: -0.0000

Data Index: 1489301 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2267. Min Act: -0.0000

Data Index: 834036 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2569. Min Act: -0.0000

Data Index: 1732418 (The Pile)

Max Activating Token Index: 690

Text #12

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.0562. Min Act: -0.0000

Data Index: 490788 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2268. Min Act: -0.0000

Data Index: 1413831 (The Pile)

Max Activating Token Index: 660

Text #14

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.2267. Min Act: -0.0000

Data Index: 1673091 (The Pile)

Max Activating Token Index: 469

Text #15

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1871. Min Act: -0.0000

Data Index: 711129 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.0212. Min Act: -0.0000

Data Index: 1673731 (The Pile)

Max Activating Token Index: 826

Text #17

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1513. Min Act: -0.0000

Data Index: 816394 (The Pile)

Max Activating Token Index: 453

Text #18

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1542. Min Act: -0.0000

Data Index: 1960504 (The Pile)

Max Activating Token Index: 477

Text #19

Max Range: 5.0668. Min Range: -5.0668

Max Act: 4.1321. Min Act: -0.0000

Data Index: 1158578 (The Pile)

Max Activating Token Index: 465