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

Dataset: The Pile

Neuron 2104 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.6459. Min Act: -0.0000

Data Index: 1686695 (The Pile)

Max Activating Token Index: 195

Text #1

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.2080. Min Act: -0.0000

Data Index: 1649997 (The Pile)

Max Activating Token Index: 815

Text #2

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.4092. Min Act: -0.0000

Data Index: 194275 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.1715. Min Act: -0.0000

Data Index: 145447 (The Pile)

Max Activating Token Index: 731

Text #4

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.1762. Min Act: -0.0000

Data Index: 893329 (The Pile)

Max Activating Token Index: 522

Text #5

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.1584. Min Act: -0.0000

Data Index: 1659034 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.1677. Min Act: -0.0000

Data Index: 786668 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.9928. Min Act: -0.0001

Data Index: 1946536 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1554339 (The Pile)

Max Activating Token Index: 635

Text #9

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1367480 (The Pile)

Max Activating Token Index: 793

Text #10

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.1947. Min Act: -0.0000

Data Index: 677554 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.9631. Min Act: -0.0000

Data Index: 821214 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1675218 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.0112. Min Act: -0.0000

Data Index: 1714320 (The Pile)

Max Activating Token Index: 365

Text #14

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.8727. Min Act: -0.0000

Data Index: 1855923 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.7591. Min Act: -0.0000

Data Index: 1284047 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.8207. Min Act: -0.0000

Data Index: 1449665 (The Pile)

Max Activating Token Index: 753

Text #17

Max Range: 1.6459. Min Range: -1.6459

Max Act: 1.1141. Min Act: -0.0000

Data Index: 1887422 (The Pile)

Max Activating Token Index: 600

Text #18

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.8665. Min Act: -0.0000

Data Index: 303254 (The Pile)

Max Activating Token Index: 785

Text #19

Max Range: 1.6459. Min Range: -1.6459

Max Act: 0.8888. Min Act: -0.0000

Data Index: 555805 (The Pile)

Max Activating Token Index: 878