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

Dataset: The Pile

Neuron 2844 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0618. Min Act: -0.0000

Data Index: 267483 (The Pile)

Max Activating Token Index: 900

Text #1

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1464298 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0586. Min Act: -0.0000

Data Index: 915758 (The Pile)

Max Activating Token Index: 770

Text #3

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1765022 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0545. Min Act: -0.0000

Data Index: 1179813 (The Pile)

Max Activating Token Index: 853

Text #5

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1829345 (The Pile)

Max Activating Token Index: 796

Text #6

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0523. Min Act: -0.0000

Data Index: 1496784 (The Pile)

Max Activating Token Index: 935

Text #7

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0530. Min Act: -0.0000

Data Index: 668527 (The Pile)

Max Activating Token Index: 907

Text #8

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0505. Min Act: -0.0000

Data Index: 521253 (The Pile)

Max Activating Token Index: 904

Text #9

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0540. Min Act: -0.0000

Data Index: 15346 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1601125 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1803934 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1041623 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0522. Min Act: -0.0000

Data Index: 1587657 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0438. Min Act: -0.0000

Data Index: 688577 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0462. Min Act: -0.0000

Data Index: 696165 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0542. Min Act: -0.0000

Data Index: 232637 (The Pile)

Max Activating Token Index: 466

Text #17

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0486. Min Act: -0.0000

Data Index: 1115099 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0435. Min Act: -0.0000

Data Index: 1405529 (The Pile)

Max Activating Token Index: 693

Text #19

Max Range: 0.0634. Min Range: -0.0634

Max Act: 0.0448. Min Act: -0.0000

Data Index: 699321 (The Pile)

Max Activating Token Index: 853