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

Dataset: The Pile

Neuron 1917 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: 1.1072. Min Range: -1.1072

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1526570 (The Pile)

Max Activating Token Index: 866

Text #1

Max Range: 1.1072. Min Range: -1.1072

Max Act: 1.0673. Min Act: -0.0000

Data Index: 1578371 (The Pile)

Max Activating Token Index: 932

Text #2

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9713. Min Act: -0.0000

Data Index: 1569146 (The Pile)

Max Activating Token Index: 586

Text #3

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9990. Min Act: -0.0000

Data Index: 1697456 (The Pile)

Max Activating Token Index: 953

Text #4

Max Range: 1.1072. Min Range: -1.1072

Max Act: 1.0035. Min Act: -0.0000

Data Index: 1170943 (The Pile)

Max Activating Token Index: 752

Text #5

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1645328 (The Pile)

Max Activating Token Index: 983

Text #6

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9423. Min Act: -0.0000

Data Index: 1850038 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 1.1072. Min Range: -1.1072

Max Act: 1.0034. Min Act: -0.0000

Data Index: 1114192 (The Pile)

Max Activating Token Index: 207

Text #8

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1675914 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9197. Min Act: -0.0000

Data Index: 911940 (The Pile)

Max Activating Token Index: 919

Text #10

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9050. Min Act: -0.0000

Data Index: 284216 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9268. Min Act: -0.0000

Data Index: 855290 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1441265 (The Pile)

Max Activating Token Index: 897

Text #13

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.8942. Min Act: -0.0000

Data Index: 460803 (The Pile)

Max Activating Token Index: 143

Text #14

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9299. Min Act: -0.0000

Data Index: 265335 (The Pile)

Max Activating Token Index: 999

Text #15

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9651. Min Act: -0.0000

Data Index: 997075 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1824522 (The Pile)

Max Activating Token Index: 481

Text #17

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1314894 (The Pile)

Max Activating Token Index: 574

Text #18

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.8966. Min Act: -0.0000

Data Index: 1261663 (The Pile)

Max Activating Token Index: 763

Text #19

Max Range: 1.1072. Min Range: -1.1072

Max Act: 0.9181. Min Act: -0.0000

Data Index: 1862672 (The Pile)

Max Activating Token Index: 126