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

Dataset: The Pile

Neuron 818 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: 0.1297. Min Range: -0.1297

Max Act: 0.1297. Min Act: -0.0000

Data Index: 435936 (The Pile)

Max Activating Token Index: 266

Text #1

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1536020 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1155487 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1144. Min Act: -0.0000

Data Index: 1352423 (The Pile)

Max Activating Token Index: 123

Text #4

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0974. Min Act: -0.0000

Data Index: 426008 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0945. Min Act: -0.0000

Data Index: 118950 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1102. Min Act: -0.0000

Data Index: 994185 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1066. Min Act: -0.0000

Data Index: 1792940 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1111. Min Act: -0.0000

Data Index: 509206 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1014. Min Act: -0.0000

Data Index: 538987 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1326946 (The Pile)

Max Activating Token Index: 217

Text #11

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0987. Min Act: -0.0000

Data Index: 1537990 (The Pile)

Max Activating Token Index: 62

Text #12

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0967. Min Act: -0.0000

Data Index: 398400 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0951. Min Act: -0.0000

Data Index: 1878866 (The Pile)

Max Activating Token Index: 73

Text #14

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0914. Min Act: -0.0000

Data Index: 138208 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.1014. Min Act: -0.0000

Data Index: 360371 (The Pile)

Max Activating Token Index: 66

Text #16

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0958. Min Act: -0.0000

Data Index: 318302 (The Pile)

Max Activating Token Index: 483

Text #17

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0992. Min Act: -0.0000

Data Index: 1468720 (The Pile)

Max Activating Token Index: 57

Text #18

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1817578 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 0.1297. Min Range: -0.1297

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1759981 (The Pile)

Max Activating Token Index: 443