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

Dataset: The Pile

Neuron 4495 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: 0.9597. Min Range: -0.9597

Max Act: 0.9597. Min Act: -0.0000

Data Index: 694609 (The Pile)

Max Activating Token Index: 843

Text #1

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8664. Min Act: -0.0000

Data Index: 872721 (The Pile)

Max Activating Token Index: 744

Text #2

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7262. Min Act: -0.0000

Data Index: 1396888 (The Pile)

Max Activating Token Index: 969

Text #3

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1132568 (The Pile)

Max Activating Token Index: 897

Text #4

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.8094. Min Act: -0.0000

Data Index: 195572 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7578. Min Act: -0.0000

Data Index: 1310790 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1835440 (The Pile)

Max Activating Token Index: 500

Text #7

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7058. Min Act: -0.0000

Data Index: 70885 (The Pile)

Max Activating Token Index: 864

Text #8

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7757. Min Act: -0.0000

Data Index: 873055 (The Pile)

Max Activating Token Index: 1007

Text #9

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6819. Min Act: -0.0000

Data Index: 1056958 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7094. Min Act: -0.0000

Data Index: 871029 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6791. Min Act: -0.0000

Data Index: 1388298 (The Pile)

Max Activating Token Index: 288

Text #12

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1427010 (The Pile)

Max Activating Token Index: 316

Text #13

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1038516 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6302. Min Act: -0.0000

Data Index: 1863624 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6182. Min Act: -0.0000

Data Index: 118462 (The Pile)

Max Activating Token Index: 903

Text #16

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6992. Min Act: -0.0000

Data Index: 533356 (The Pile)

Max Activating Token Index: 635

Text #17

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6749. Min Act: -0.0000

Data Index: 965454 (The Pile)

Max Activating Token Index: 965

Text #18

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1195139 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.9597. Min Range: -0.9597

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1641806 (The Pile)

Max Activating Token Index: 797