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

Dataset: The Pile

Neuron 305 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.8262. Min Act: -0.0000

Data Index: 247673 (The Pile)

Max Activating Token Index: 804

Text #1

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.9926. Min Act: -0.0000

Data Index: 1511568 (The Pile)

Max Activating Token Index: 201

Text #2

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7985. Min Act: -0.0000

Data Index: 1516913 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.8512. Min Act: -0.0000

Data Index: 164039 (The Pile)

Max Activating Token Index: 256

Text #4

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7991. Min Act: -0.0000

Data Index: 304748 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.7102. Min Act: -0.0000

Data Index: 1956404 (The Pile)

Max Activating Token Index: 949

Text #6

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6910. Min Act: -0.0000

Data Index: 376649 (The Pile)

Max Activating Token Index: 153

Text #7

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6945. Min Act: -0.0000

Data Index: 1738647 (The Pile)

Max Activating Token Index: 1020

Text #8

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.9021. Min Act: -0.0000

Data Index: 1458952 (The Pile)

Max Activating Token Index: 816

Text #9

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.8448. Min Act: -0.0000

Data Index: 1457646 (The Pile)

Max Activating Token Index: 924

Text #10

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.5911. Min Act: -0.0000

Data Index: 1049743 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6370. Min Act: -0.0000

Data Index: 1103831 (The Pile)

Max Activating Token Index: 134

Text #12

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.5959. Min Act: -0.0000

Data Index: 1303481 (The Pile)

Max Activating Token Index: 367

Text #13

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6203. Min Act: -0.0000

Data Index: 1971873 (The Pile)

Max Activating Token Index: 531

Text #14

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.5964. Min Act: -0.0000

Data Index: 1573200 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.4921. Min Act: -0.0000

Data Index: 1664859 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6685. Min Act: -0.0000

Data Index: 375792 (The Pile)

Max Activating Token Index: 201

Text #17

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.5984. Min Act: -0.0000

Data Index: 807442 (The Pile)

Max Activating Token Index: 569

Text #18

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.6978. Min Act: -0.0000

Data Index: 842588 (The Pile)

Max Activating Token Index: 789

Text #19

Max Range: 1.9926. Min Range: -1.9926

Max Act: 1.5989. Min Act: -0.0000

Data Index: 772781 (The Pile)

Max Activating Token Index: 439