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

Dataset: The Pile

Neuron 1448 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: 1.9646. Min Range: -1.9646

Max Act: 1.7646. Min Act: -0.0000

Data Index: 655515 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.9646. Min Act: -0.0000

Data Index: 1192905 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7487. Min Act: -0.0000

Data Index: 662883 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7086. Min Act: -0.0000

Data Index: 388853 (The Pile)

Max Activating Token Index: 595

Text #4

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5918. Min Act: -0.0000

Data Index: 1566861 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7607. Min Act: -0.0000

Data Index: 1664583 (The Pile)

Max Activating Token Index: 996

Text #6

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.6861. Min Act: -0.0000

Data Index: 276967 (The Pile)

Max Activating Token Index: 75

Text #7

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7286. Min Act: -0.0000

Data Index: 1839871 (The Pile)

Max Activating Token Index: 484

Text #8

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.6560. Min Act: -0.0000

Data Index: 1433061 (The Pile)

Max Activating Token Index: 470

Text #9

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.7289. Min Act: -0.0000

Data Index: 1342134 (The Pile)

Max Activating Token Index: 799

Text #10

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.6429. Min Act: -0.0000

Data Index: 183600 (The Pile)

Max Activating Token Index: 895

Text #11

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5392. Min Act: -0.0000

Data Index: 1310942 (The Pile)

Max Activating Token Index: 111

Text #12

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.6150. Min Act: -0.0000

Data Index: 524495 (The Pile)

Max Activating Token Index: 900

Text #13

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5313. Min Act: -0.0000

Data Index: 1369832 (The Pile)

Max Activating Token Index: 710

Text #14

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5729. Min Act: -0.0000

Data Index: 10824 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5700. Min Act: -0.0000

Data Index: 1052603 (The Pile)

Max Activating Token Index: 814

Text #16

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5704. Min Act: -0.0000

Data Index: 1121749 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5599. Min Act: -0.0000

Data Index: 1700740 (The Pile)

Max Activating Token Index: 901

Text #18

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.5552. Min Act: -0.0000

Data Index: 1698627 (The Pile)

Max Activating Token Index: 609

Text #19

Max Range: 1.9646. Min Range: -1.9646

Max Act: 1.4783. Min Act: -0.0000

Data Index: 1611568 (The Pile)

Max Activating Token Index: 736