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

Dataset: The Pile

Neuron 1642 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.1949. Min Act: -0.0000

Data Index: 778750 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9575. Min Act: -0.0000

Data Index: 1749086 (The Pile)

Max Activating Token Index: 96

Text #2

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8745. Min Act: -0.0000

Data Index: 847589 (The Pile)

Max Activating Token Index: 421

Text #3

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8934. Min Act: -0.0000

Data Index: 385741 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8952. Min Act: -0.0000

Data Index: 1567604 (The Pile)

Max Activating Token Index: 556

Text #5

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8134. Min Act: -0.0000

Data Index: 567591 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1983207 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8636. Min Act: -0.0000

Data Index: 1320254 (The Pile)

Max Activating Token Index: 625

Text #8

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8808. Min Act: -0.0000

Data Index: 905668 (The Pile)

Max Activating Token Index: 717

Text #9

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7735. Min Act: -0.0000

Data Index: 434372 (The Pile)

Max Activating Token Index: 454

Text #10

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7932. Min Act: -0.0000

Data Index: 780534 (The Pile)

Max Activating Token Index: 528

Text #11

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1618920 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1851065 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7614. Min Act: -0.0000

Data Index: 335181 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7697. Min Act: -0.0000

Data Index: 1876069 (The Pile)

Max Activating Token Index: 238

Text #15

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8159. Min Act: -0.0000

Data Index: 655427 (The Pile)

Max Activating Token Index: 995

Text #16

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8122. Min Act: -0.0000

Data Index: 1910207 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7393. Min Act: -0.0000

Data Index: 1868620 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1598028 (The Pile)

Max Activating Token Index: 985

Text #19

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.7710. Min Act: -0.0000

Data Index: 446854 (The Pile)

Max Activating Token Index: 677