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

Dataset: The Pile

Neuron 1258 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: 1.2324. Min Range: -1.2324

Max Act: 1.2324. Min Act: -0.0000

Data Index: 970506 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.1677. Min Act: -0.0000

Data Index: 1815751 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.1450. Min Act: -0.0000

Data Index: 1722044 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1902623 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1666823 (The Pile)

Max Activating Token Index: 668

Text #5

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.1280. Min Act: -0.0000

Data Index: 212018 (The Pile)

Max Activating Token Index: 138

Text #6

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1095657 (The Pile)

Max Activating Token Index: 702

Text #7

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0453. Min Act: -0.0000

Data Index: 804310 (The Pile)

Max Activating Token Index: 338

Text #8

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0990. Min Act: -0.0000

Data Index: 654047 (The Pile)

Max Activating Token Index: 330

Text #9

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0602. Min Act: -0.0000

Data Index: 1668610 (The Pile)

Max Activating Token Index: 42

Text #10

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0515. Min Act: -0.0000

Data Index: 960529 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1191735 (The Pile)

Max Activating Token Index: 303

Text #12

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0183. Min Act: -0.0000

Data Index: 260045 (The Pile)

Max Activating Token Index: 578

Text #13

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0596. Min Act: -0.0000

Data Index: 973720 (The Pile)

Max Activating Token Index: 395

Text #14

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9919. Min Act: -0.0000

Data Index: 1217137 (The Pile)

Max Activating Token Index: 646

Text #15

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0408. Min Act: -0.0000

Data Index: 419513 (The Pile)

Max Activating Token Index: 227

Text #16

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0767. Min Act: -0.0000

Data Index: 881770 (The Pile)

Max Activating Token Index: 454

Text #17

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0169. Min Act: -0.0000

Data Index: 1592631 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 1.2324. Min Range: -1.2324

Max Act: 0.9793. Min Act: -0.0000

Data Index: 453850 (The Pile)

Max Activating Token Index: 150

Text #19

Max Range: 1.2324. Min Range: -1.2324

Max Act: 1.0441. Min Act: -0.0000

Data Index: 639738 (The Pile)

Max Activating Token Index: 418