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

Dataset: The Pile

Neuron 450 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.7276. Min Act: -0.0000

Data Index: 1277252 (The Pile)

Max Activating Token Index: 747

Text #1

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.8018. Min Act: -0.0000

Data Index: 1543941 (The Pile)

Max Activating Token Index: 977

Text #2

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.5973. Min Act: -0.0000

Data Index: 1845441 (The Pile)

Max Activating Token Index: 867

Text #3

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.6653. Min Act: -0.0000

Data Index: 1903337 (The Pile)

Max Activating Token Index: 132

Text #4

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.6516. Min Act: -0.0000

Data Index: 1859817 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.4522. Min Act: -0.0000

Data Index: 985657 (The Pile)

Max Activating Token Index: 116

Text #6

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.4429. Min Act: -0.0000

Data Index: 319225 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.3622. Min Act: -0.0000

Data Index: 330626 (The Pile)

Max Activating Token Index: 671

Text #8

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2904. Min Act: -0.0000

Data Index: 682718 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2525. Min Act: -0.0000

Data Index: 532641 (The Pile)

Max Activating Token Index: 751

Text #10

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.1747. Min Act: -0.0000

Data Index: 889875 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2975. Min Act: -0.0000

Data Index: 653099 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2916. Min Act: 0.0000

Data Index: 216832 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2877. Min Act: -0.0000

Data Index: 1759900 (The Pile)

Max Activating Token Index: 129

Text #14

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1047459 (The Pile)

Max Activating Token Index: 795

Text #15

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2005. Min Act: -0.0000

Data Index: 179769 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2065. Min Act: -0.0000

Data Index: 1864867 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.2639. Min Act: -0.0000

Data Index: 503469 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.3146. Min Act: -0.0000

Data Index: 1462809 (The Pile)

Max Activating Token Index: 999

Text #19

Max Range: 1.8018. Min Range: -1.8018

Max Act: 1.1662. Min Act: -0.0000

Data Index: 1581052 (The Pile)

Max Activating Token Index: 198