Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 141 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.3676. Min Act: -0.0000

Data Index: 1460080 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.3261. Min Act: -0.0000

Data Index: 989854 (The Pile)

Max Activating Token Index: 199

Text #2

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.2646. Min Act: -0.0000

Data Index: 1953875 (The Pile)

Max Activating Token Index: 370

Text #3

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.1898. Min Act: -0.0000

Data Index: 355585 (The Pile)

Max Activating Token Index: 940

Text #4

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.1433. Min Act: -0.0000

Data Index: 129524 (The Pile)

Max Activating Token Index: 950

Text #5

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1289109 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.0229. Min Act: -0.0000

Data Index: 365333 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.2045. Min Act: -0.0000

Data Index: 1031356 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1565659 (The Pile)

Max Activating Token Index: 983

Text #9

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.1093. Min Act: -0.0000

Data Index: 1526176 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.1082. Min Act: -0.0000

Data Index: 837329 (The Pile)

Max Activating Token Index: 568

Text #11

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.1005. Min Act: -0.0000

Data Index: 846713 (The Pile)

Max Activating Token Index: 862

Text #12

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.0264. Min Act: -0.0000

Data Index: 1191840 (The Pile)

Max Activating Token Index: 162

Text #13

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.0762. Min Act: -0.0000

Data Index: 201821 (The Pile)

Max Activating Token Index: 477

Text #14

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.0810. Min Act: -0.0000

Data Index: 783242 (The Pile)

Max Activating Token Index: 744

Text #15

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.1384. Min Act: -0.0000

Data Index: 171155 (The Pile)

Max Activating Token Index: 526

Text #16

Max Range: 1.3676. Min Range: -1.3676

Max Act: 0.9779. Min Act: -0.0000

Data Index: 1450347 (The Pile)

Max Activating Token Index: 82

Text #17

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.0682. Min Act: -0.0000

Data Index: 1709259 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 1.3676. Min Range: -1.3676

Max Act: 1.0470. Min Act: -0.0000

Data Index: 1119357 (The Pile)

Max Activating Token Index: 341

Text #19

Max Range: 1.3676. Min Range: -1.3676

Max Act: 0.9496. Min Act: -0.0000

Data Index: 290248 (The Pile)

Max Activating Token Index: 560