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

Dataset: The Pile

Neuron 276 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0685. Min Act: 0.0000

Data Index: 1218888 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0704. Min Act: -0.0000

Data Index: 765277 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0699. Min Act: -0.0000

Data Index: 29339 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1629384 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0694. Min Act: -0.0000

Data Index: 37701 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0692. Min Act: -0.0000

Data Index: 69170 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0687. Min Act: -0.0000

Data Index: 978193 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1709158 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0682. Min Act: -0.0000

Data Index: 934628 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0680. Min Act: -0.0000

Data Index: 751921 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0678. Min Act: -0.0000

Data Index: 188135 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0676. Min Act: -0.0000

Data Index: 238390 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1792582 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0693. Min Act: -0.0000

Data Index: 8967 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1016875 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0665. Min Act: 0.0000

Data Index: 947164 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0663. Min Act: -0.0000

Data Index: 712035 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0686. Min Act: -0.0000

Data Index: 1262348 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0661. Min Act: -0.0000

Data Index: 1361159 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0704. Min Range: -0.0704

Max Act: 0.0658. Min Act: -0.0000

Data Index: 895236 (The Pile)

Max Activating Token Index: 1023