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

Dataset: The Pile

Neuron 1071 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0829. Min Range: -1.0829

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1264278 (The Pile)

Max Activating Token Index: 592

Text #1

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9407. Min Act: -0.0000

Data Index: 1957888 (The Pile)

Max Activating Token Index: 506

Text #2

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1947631 (The Pile)

Max Activating Token Index: 523

Text #3

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8481. Min Act: -0.0000

Data Index: 1439713 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8711. Min Act: -0.0000

Data Index: 1025261 (The Pile)

Max Activating Token Index: 69

Text #5

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8825. Min Act: -0.0000

Data Index: 1684850 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8537. Min Act: -0.0000

Data Index: 1144666 (The Pile)

Max Activating Token Index: 789

Text #7

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8497. Min Act: 0.0000

Data Index: 830288 (The Pile)

Max Activating Token Index: 349

Text #8

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8233. Min Act: -0.0000

Data Index: 813705 (The Pile)

Max Activating Token Index: 95

Text #9

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7955. Min Act: -0.0000

Data Index: 1214514 (The Pile)

Max Activating Token Index: 385

Text #10

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7665. Min Act: -0.0000

Data Index: 165479 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8037. Min Act: -0.0000

Data Index: 1876915 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1993996 (The Pile)

Max Activating Token Index: 79

Text #13

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7524. Min Act: 0.0000

Data Index: 900238 (The Pile)

Max Activating Token Index: 67

Text #14

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7444. Min Act: 0.0000

Data Index: 1807047 (The Pile)

Max Activating Token Index: 93

Text #15

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7808. Min Act: -0.0000

Data Index: 1760446 (The Pile)

Max Activating Token Index: 583

Text #16

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7283. Min Act: -0.0000

Data Index: 729561 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7705. Min Act: 0.0000

Data Index: 1496142 (The Pile)

Max Activating Token Index: 142

Text #18

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.7700. Min Act: -0.0000

Data Index: 1487076 (The Pile)

Max Activating Token Index: 130

Text #19

Max Range: 1.0829. Min Range: -1.0829

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1657031 (The Pile)

Max Activating Token Index: 846