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

Dataset: The Pile

Neuron 2963 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: 5.8861. Min Range: -5.8861

Max Act: 5.8861. Min Act: -0.0000

Data Index: 949104 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.4461. Min Act: -0.0000

Data Index: 174444 (The Pile)

Max Activating Token Index: 34

Text #2

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.1350. Min Act: -0.0000

Data Index: 1900564 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.2453. Min Act: -0.0000

Data Index: 1830658 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.9093. Min Act: -0.0000

Data Index: 871601 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.0534. Min Act: -0.0000

Data Index: 521777 (The Pile)

Max Activating Token Index: 387

Text #6

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.0577. Min Act: -0.0000

Data Index: 117420 (The Pile)

Max Activating Token Index: 617

Text #7

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.0223. Min Act: -0.0000

Data Index: 1372014 (The Pile)

Max Activating Token Index: 403

Text #8

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.7464. Min Act: -0.0000

Data Index: 375886 (The Pile)

Max Activating Token Index: 810

Text #9

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.7665. Min Act: -0.0000

Data Index: 826651 (The Pile)

Max Activating Token Index: 67

Text #10

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.7524. Min Act: -0.0000

Data Index: 1801947 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.8902. Min Act: -0.0000

Data Index: 1412773 (The Pile)

Max Activating Token Index: 426

Text #12

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.7303. Min Act: -0.0000

Data Index: 736267 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.8769. Min Act: -0.0000

Data Index: 817286 (The Pile)

Max Activating Token Index: 640

Text #14

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.8633. Min Act: -0.0000

Data Index: 1397554 (The Pile)

Max Activating Token Index: 655

Text #15

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.0614. Min Act: -0.0000

Data Index: 1111177 (The Pile)

Max Activating Token Index: 830

Text #16

Max Range: 5.8861. Min Range: -5.8861

Max Act: 5.0583. Min Act: -0.0000

Data Index: 600512 (The Pile)

Max Activating Token Index: 525

Text #17

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.8475. Min Act: -0.0000

Data Index: 1352815 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.8351. Min Act: -0.0000

Data Index: 1420396 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 5.8861. Min Range: -5.8861

Max Act: 4.8230. Min Act: -0.0000

Data Index: 812765 (The Pile)

Max Activating Token Index: 671