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

Dataset: The Pile

Neuron 4620 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.3116. Min Act: -0.0000

Data Index: 644249 (The Pile)

Max Activating Token Index: 967

Text #1

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2625. Min Act: -0.0000

Data Index: 1887407 (The Pile)

Max Activating Token Index: 323

Text #2

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2682. Min Act: -0.0000

Data Index: 1242555 (The Pile)

Max Activating Token Index: 702

Text #3

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2616. Min Act: -0.0000

Data Index: 750715 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2665. Min Act: -0.0001

Data Index: 1564637 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2552. Min Act: -0.0000

Data Index: 1914610 (The Pile)

Max Activating Token Index: 682

Text #6

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2461. Min Act: -0.0000

Data Index: 565814 (The Pile)

Max Activating Token Index: 800

Text #7

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1178957 (The Pile)

Max Activating Token Index: 307

Text #8

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2475. Min Act: -0.0000

Data Index: 899068 (The Pile)

Max Activating Token Index: 758

Text #9

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2275. Min Act: -0.0000

Data Index: 973168 (The Pile)

Max Activating Token Index: 648

Text #10

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1618553 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2316. Min Act: -0.0001

Data Index: 462205 (The Pile)

Max Activating Token Index: 413

Text #12

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2099. Min Act: -0.0000

Data Index: 323171 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2063. Min Act: -0.0001

Data Index: 1035456 (The Pile)

Max Activating Token Index: 368

Text #14

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1931. Min Act: -0.0000

Data Index: 1068752 (The Pile)

Max Activating Token Index: 998

Text #15

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2084. Min Act: -0.0000

Data Index: 1196654 (The Pile)

Max Activating Token Index: 396

Text #16

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1627140 (The Pile)

Max Activating Token Index: 754

Text #17

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2125. Min Act: -0.0000

Data Index: 1873651 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.2032. Min Act: -0.0000

Data Index: 637920 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 0.3116. Min Range: -0.3116

Max Act: 0.1994. Min Act: -0.0000

Data Index: 857972 (The Pile)

Max Activating Token Index: 181