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

Dataset: The Pile

Neuron 3636 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: 0.3607. Min Range: -0.3607

Max Act: 0.3607. Min Act: -0.0000

Data Index: 1222213 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3396. Min Act: -0.0000

Data Index: 1290730 (The Pile)

Max Activating Token Index: 757

Text #2

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3358. Min Act: -0.0000

Data Index: 981295 (The Pile)

Max Activating Token Index: 601

Text #3

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.3133. Min Act: -0.0000

Data Index: 885690 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2814. Min Act: -0.0000

Data Index: 791202 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2484. Min Act: -0.0000

Data Index: 41113 (The Pile)

Max Activating Token Index: 852

Text #6

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2872. Min Act: -0.0000

Data Index: 1746868 (The Pile)

Max Activating Token Index: 84

Text #7

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2969. Min Act: -0.0000

Data Index: 1764712 (The Pile)

Max Activating Token Index: 847

Text #8

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2704. Min Act: -0.0000

Data Index: 395833 (The Pile)

Max Activating Token Index: 775

Text #9

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2582. Min Act: -0.0000

Data Index: 1408957 (The Pile)

Max Activating Token Index: 323

Text #10

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2542. Min Act: -0.0000

Data Index: 455271 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2566. Min Act: -0.0000

Data Index: 1677092 (The Pile)

Max Activating Token Index: 234

Text #12

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2426. Min Act: -0.0000

Data Index: 1976944 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2537. Min Act: -0.0000

Data Index: 1095558 (The Pile)

Max Activating Token Index: 499

Text #14

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1850600 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2528. Min Act: -0.0000

Data Index: 450109 (The Pile)

Max Activating Token Index: 486

Text #16

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1982360 (The Pile)

Max Activating Token Index: 338

Text #17

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1347368 (The Pile)

Max Activating Token Index: 17

Text #18

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1220783 (The Pile)

Max Activating Token Index: 922

Text #19

Max Range: 0.3607. Min Range: -0.3607

Max Act: 0.2489. Min Act: -0.0000

Data Index: 28134 (The Pile)

Max Activating Token Index: 237