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

Dataset: The Pile

Neuron 0 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: 3.1609. Min Range: -3.1609

Max Act: 3.1609. Min Act: -0.0000

Data Index: 766970 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 3.1609. Min Range: -3.1609

Max Act: 3.0041. Min Act: -0.0000

Data Index: 684532 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 3.1609. Min Range: -3.1609

Max Act: 3.0719. Min Act: -0.0000

Data Index: 739799 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.6758. Min Act: -0.0000

Data Index: 248275 (The Pile)

Max Activating Token Index: 557

Text #4

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.7998. Min Act: -0.0000

Data Index: 1448045 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.7678. Min Act: -0.0000

Data Index: 192749 (The Pile)

Max Activating Token Index: 356

Text #6

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.7560. Min Act: -0.0000

Data Index: 1891332 (The Pile)

Max Activating Token Index: 866

Text #7

Max Range: 3.1609. Min Range: -3.1609

Max Act: 3.0071. Min Act: -0.0000

Data Index: 684065 (The Pile)

Max Activating Token Index: 920

Text #8

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.7600. Min Act: -0.0000

Data Index: 1895111 (The Pile)

Max Activating Token Index: 422

Text #9

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.4385. Min Act: -0.0000

Data Index: 931660 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.4006. Min Act: -0.0000

Data Index: 1618754 (The Pile)

Max Activating Token Index: 190

Text #11

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.6491. Min Act: -0.0000

Data Index: 1619090 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.8994. Min Act: -0.0000

Data Index: 490938 (The Pile)

Max Activating Token Index: 1020

Text #13

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.6131. Min Act: -0.0000

Data Index: 445268 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.6094. Min Act: -0.0000

Data Index: 1569194 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.7489. Min Act: -0.0000

Data Index: 1919277 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.5966. Min Act: -0.0000

Data Index: 468524 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.6083. Min Act: -0.0000

Data Index: 1871499 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.7110. Min Act: -0.0000

Data Index: 819049 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 3.1609. Min Range: -3.1609

Max Act: 2.7095. Min Act: -0.0000

Data Index: 716571 (The Pile)

Max Activating Token Index: 466