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

Dataset: The Pile

Neuron 1889 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.8476. Min Act: -0.0000

Data Index: 1532793 (The Pile)

Max Activating Token Index: 874

Text #1

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.7484. Min Act: -0.0000

Data Index: 610864 (The Pile)

Max Activating Token Index: 622

Text #2

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.5003. Min Act: -0.0000

Data Index: 27167 (The Pile)

Max Activating Token Index: 476

Text #3

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1337190 (The Pile)

Max Activating Token Index: 173

Text #4

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1947. Min Act: -0.0000

Data Index: 119246 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.3321. Min Act: -0.0000

Data Index: 916485 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2393. Min Act: -0.0000

Data Index: 1620400 (The Pile)

Max Activating Token Index: 423

Text #7

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1593. Min Act: -0.0000

Data Index: 1229547 (The Pile)

Max Activating Token Index: 743

Text #8

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2126. Min Act: -0.0000

Data Index: 31855 (The Pile)

Max Activating Token Index: 246

Text #9

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.2113. Min Act: -0.0000

Data Index: 153339 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1967. Min Act: -0.0000

Data Index: 201306 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1785763 (The Pile)

Max Activating Token Index: 100

Text #12

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1791368 (The Pile)

Max Activating Token Index: 997

Text #13

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.0725. Min Act: -0.0000

Data Index: 972076 (The Pile)

Max Activating Token Index: 451

Text #14

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1421. Min Act: -0.0000

Data Index: 484842 (The Pile)

Max Activating Token Index: 909

Text #15

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1678729 (The Pile)

Max Activating Token Index: 142

Text #16

Max Range: 1.8476. Min Range: -1.8476

Max Act: 0.9913. Min Act: -0.0000

Data Index: 1134433 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1255483 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.0930. Min Act: -0.0000

Data Index: 1654460 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 1.8476. Min Range: -1.8476

Max Act: 1.0770. Min Act: -0.0000

Data Index: 471841 (The Pile)

Max Activating Token Index: 601