Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 975 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1007. Min Act: -0.0004

Data Index: 160184 (The Pile)

Max Activating Token Index: 94

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0996. Min Act: -0.0004

Data Index: 1845295 (The Pile)

Max Activating Token Index: 303

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0004

Data Index: 1327286 (The Pile)

Max Activating Token Index: 143

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0933. Min Act: -0.0004

Data Index: 435638 (The Pile)

Max Activating Token Index: 52

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0927. Min Act: -0.0004

Data Index: 1295435 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0894. Min Act: -0.0004

Data Index: 861098 (The Pile)

Max Activating Token Index: 42

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0910. Min Act: -0.0004

Data Index: 1328833 (The Pile)

Max Activating Token Index: 957

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0933. Min Act: -0.0004

Data Index: 1361812 (The Pile)

Max Activating Token Index: 67

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0860. Min Act: -0.0004

Data Index: 1378130 (The Pile)

Max Activating Token Index: 753

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0887. Min Act: -0.0004

Data Index: 48434 (The Pile)

Max Activating Token Index: 442

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0871. Min Act: -0.0004

Data Index: 1695554 (The Pile)

Max Activating Token Index: 243

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0863. Min Act: -0.0004

Data Index: 1029551 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0819. Min Act: -0.0004

Data Index: 252645 (The Pile)

Max Activating Token Index: 150

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0908. Min Act: -0.0004

Data Index: 1835640 (The Pile)

Max Activating Token Index: 211

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0824. Min Act: -0.0004

Data Index: 1540878 (The Pile)

Max Activating Token Index: 174

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0828. Min Act: -0.0004

Data Index: 1595266 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0820. Min Act: -0.0004

Data Index: 664352 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0796. Min Act: -0.0004

Data Index: 1914127 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0823. Min Act: -0.0004

Data Index: 1375755 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0822. Min Act: -0.0004

Data Index: 864476 (The Pile)

Max Activating Token Index: 283