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

Dataset: The Pile

Neuron 1208 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1784786 (The Pile)

Max Activating Token Index: 439

Text #1

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1962. Min Act: -0.0000

Data Index: 232316 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1462. Min Act: -0.0000

Data Index: 553833 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1270. Min Act: -0.0000

Data Index: 704462 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1206. Min Act: -0.0000

Data Index: 1705375 (The Pile)

Max Activating Token Index: 981

Text #5

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1149. Min Act: -0.0000

Data Index: 182580 (The Pile)

Max Activating Token Index: 77

Text #6

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1109731 (The Pile)

Max Activating Token Index: 919

Text #7

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1184. Min Act: -0.0000

Data Index: 808453 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1364941 (The Pile)

Max Activating Token Index: 673

Text #9

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1108. Min Act: -0.0000

Data Index: 266033 (The Pile)

Max Activating Token Index: 980

Text #10

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1744886 (The Pile)

Max Activating Token Index: 1006

Text #11

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.0931. Min Act: -0.0000

Data Index: 729129 (The Pile)

Max Activating Token Index: 289

Text #12

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1388135 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1079. Min Act: -0.0000

Data Index: 1625527 (The Pile)

Max Activating Token Index: 900

Text #14

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.0995. Min Act: -0.0000

Data Index: 240497 (The Pile)

Max Activating Token Index: 934

Text #15

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1065. Min Act: -0.0000

Data Index: 255892 (The Pile)

Max Activating Token Index: 805

Text #16

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1723533 (The Pile)

Max Activating Token Index: 773

Text #17

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1050. Min Act: -0.0000

Data Index: 23560 (The Pile)

Max Activating Token Index: 771

Text #18

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1478792 (The Pile)

Max Activating Token Index: 677

Text #19

Max Range: 0.2140. Min Range: -0.2140

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1624127 (The Pile)

Max Activating Token Index: 467