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

Dataset: The Pile

Neuron 3731 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7785. Min Range: -3.7785

Max Act: 3.7785. Min Act: -0.0000

Data Index: 1691030 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 3.7785. Min Range: -3.7785

Max Act: 3.4682. Min Act: -0.0000

Data Index: 138380 (The Pile)

Max Activating Token Index: 132

Text #2

Max Range: 3.7785. Min Range: -3.7785

Max Act: 3.3639. Min Act: -0.0000

Data Index: 1179975 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 3.7785. Min Range: -3.7785

Max Act: 3.4690. Min Act: -0.0000

Data Index: 1825207 (The Pile)

Max Activating Token Index: 402

Text #4

Max Range: 3.7785. Min Range: -3.7785

Max Act: 3.2946. Min Act: -0.0000

Data Index: 1051551 (The Pile)

Max Activating Token Index: 669

Text #5

Max Range: 3.7785. Min Range: -3.7785

Max Act: 3.3198. Min Act: -0.0000

Data Index: 1118120 (The Pile)

Max Activating Token Index: 843

Text #6

Max Range: 3.7785. Min Range: -3.7785

Max Act: 3.2447. Min Act: -0.0000

Data Index: 358122 (The Pile)

Max Activating Token Index: 289

Text #7

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.6364. Min Act: -0.0000

Data Index: 1141349 (The Pile)

Max Activating Token Index: 826

Text #8

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.7885. Min Act: -0.0000

Data Index: 1111885 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.8397. Min Act: -0.0000

Data Index: 850448 (The Pile)

Max Activating Token Index: 289

Text #10

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.5902. Min Act: -0.0000

Data Index: 1380766 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.8147. Min Act: -0.0000

Data Index: 1870795 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.9257. Min Act: -0.0000

Data Index: 97814 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.5076. Min Act: -0.0000

Data Index: 1390088 (The Pile)

Max Activating Token Index: 931

Text #14

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.7656. Min Act: -0.0000

Data Index: 1702030 (The Pile)

Max Activating Token Index: 269

Text #15

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.7442. Min Act: -0.0000

Data Index: 1373371 (The Pile)

Max Activating Token Index: 207

Text #16

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.5917. Min Act: -0.0000

Data Index: 1643533 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.5747. Min Act: -0.0000

Data Index: 670764 (The Pile)

Max Activating Token Index: 522

Text #18

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.4361. Min Act: -0.0000

Data Index: 727329 (The Pile)

Max Activating Token Index: 83

Text #19

Max Range: 3.7785. Min Range: -3.7785

Max Act: 2.4484. Min Act: -0.0000

Data Index: 1719194 (The Pile)

Max Activating Token Index: 657