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

Dataset: The Pile

Neuron 2056 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: 4.4322. Min Range: -4.4322

Max Act: 4.4322. Min Act: -0.0000

Data Index: 496137 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.3424. Min Act: -0.0000

Data Index: 1557986 (The Pile)

Max Activating Token Index: 13

Text #2

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9742. Min Act: -0.0000

Data Index: 589948 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.3950. Min Act: -0.0000

Data Index: 754386 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.2164. Min Act: -0.0000

Data Index: 827363 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.0303. Min Act: -0.0000

Data Index: 1642079 (The Pile)

Max Activating Token Index: 157

Text #6

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.1482. Min Act: -0.0000

Data Index: 1198620 (The Pile)

Max Activating Token Index: 374

Text #7

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.1322. Min Act: -0.0000

Data Index: 1915506 (The Pile)

Max Activating Token Index: 98

Text #8

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9100. Min Act: -0.0000

Data Index: 1935038 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.7263. Min Act: -0.0000

Data Index: 1316149 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.8733. Min Act: -0.0000

Data Index: 1200410 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.8645. Min Act: -0.0000

Data Index: 916694 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9822. Min Act: -0.0000

Data Index: 1832603 (The Pile)

Max Activating Token Index: 46

Text #13

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9413. Min Act: -0.0000

Data Index: 1508388 (The Pile)

Max Activating Token Index: 200

Text #14

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.9196. Min Act: -0.0000

Data Index: 687012 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.7613. Min Act: -0.0000

Data Index: 12014 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.8989. Min Act: -0.0000

Data Index: 1412936 (The Pile)

Max Activating Token Index: 266

Text #17

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.7517. Min Act: -0.0000

Data Index: 1464513 (The Pile)

Max Activating Token Index: 598

Text #18

Max Range: 4.4322. Min Range: -4.4322

Max Act: 4.1542. Min Act: -0.0000

Data Index: 1750139 (The Pile)

Max Activating Token Index: 39

Text #19

Max Range: 4.4322. Min Range: -4.4322

Max Act: 3.8344. Min Act: -0.0000

Data Index: 835802 (The Pile)

Max Activating Token Index: 46