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

Dataset: The Pile

Neuron 1970 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.1060. Min Act: -0.0000

Data Index: 263834 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0803. Min Act: -0.0000

Data Index: 582720 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0024. Min Act: -0.0000

Data Index: 1248071 (The Pile)

Max Activating Token Index: 928

Text #3

Max Range: 1.1060. Min Range: -1.1060

Max Act: 1.0181. Min Act: -0.0000

Data Index: 1542044 (The Pile)

Max Activating Token Index: 248

Text #4

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7664. Min Act: -0.0000

Data Index: 1932020 (The Pile)

Max Activating Token Index: 897

Text #5

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1623205 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8632. Min Act: -0.0000

Data Index: 278291 (The Pile)

Max Activating Token Index: 80

Text #7

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8452. Min Act: -0.0000

Data Index: 167629 (The Pile)

Max Activating Token Index: 765

Text #8

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8435. Min Act: -0.0000

Data Index: 917854 (The Pile)

Max Activating Token Index: 144

Text #9

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8127. Min Act: -0.0000

Data Index: 397223 (The Pile)

Max Activating Token Index: 606

Text #10

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8006. Min Act: -0.0000

Data Index: 830518 (The Pile)

Max Activating Token Index: 552

Text #11

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7864. Min Act: -0.0000

Data Index: 241913 (The Pile)

Max Activating Token Index: 80

Text #12

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7751. Min Act: -0.0000

Data Index: 1968270 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7748. Min Act: -0.0000

Data Index: 971282 (The Pile)

Max Activating Token Index: 742

Text #14

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1456453 (The Pile)

Max Activating Token Index: 228

Text #15

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7190. Min Act: -0.0000

Data Index: 1165916 (The Pile)

Max Activating Token Index: 866

Text #16

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.7553. Min Act: -0.0000

Data Index: 537807 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1553644 (The Pile)

Max Activating Token Index: 156

Text #18

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.6871. Min Act: -0.0000

Data Index: 307114 (The Pile)

Max Activating Token Index: 60

Text #19

Max Range: 1.1060. Min Range: -1.1060

Max Act: 0.8084. Min Act: -0.0000

Data Index: 643045 (The Pile)

Max Activating Token Index: 798