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

Dataset: The Pile

Neuron 1333 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: 0.9475. Min Range: -0.9475

Max Act: 0.9475. Min Act: -0.0000

Data Index: 574837 (The Pile)

Max Activating Token Index: 744

Text #1

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.9116. Min Act: -0.0000

Data Index: 365167 (The Pile)

Max Activating Token Index: 66

Text #2

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.8100. Min Act: -0.0000

Data Index: 268623 (The Pile)

Max Activating Token Index: 285

Text #3

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.8048. Min Act: -0.0000

Data Index: 1254271 (The Pile)

Max Activating Token Index: 892

Text #4

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1153612 (The Pile)

Max Activating Token Index: 121

Text #5

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1816473 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7282. Min Act: -0.0000

Data Index: 558805 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6894. Min Act: -0.0000

Data Index: 712574 (The Pile)

Max Activating Token Index: 771

Text #8

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7100. Min Act: -0.0000

Data Index: 1340751 (The Pile)

Max Activating Token Index: 421

Text #9

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7080. Min Act: -0.0000

Data Index: 1517748 (The Pile)

Max Activating Token Index: 64

Text #10

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6757. Min Act: -0.0000

Data Index: 845093 (The Pile)

Max Activating Token Index: 245

Text #11

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1161145 (The Pile)

Max Activating Token Index: 311

Text #12

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6958. Min Act: -0.0000

Data Index: 449256 (The Pile)

Max Activating Token Index: 757

Text #13

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6935. Min Act: -0.0000

Data Index: 175188 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1943418 (The Pile)

Max Activating Token Index: 279

Text #15

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1841259 (The Pile)

Max Activating Token Index: 46

Text #16

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.7095. Min Act: -0.0000

Data Index: 1413169 (The Pile)

Max Activating Token Index: 513

Text #17

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6860. Min Act: -0.0000

Data Index: 210703 (The Pile)

Max Activating Token Index: 300

Text #18

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6826. Min Act: -0.0000

Data Index: 1346586 (The Pile)

Max Activating Token Index: 181

Text #19

Max Range: 0.9475. Min Range: -0.9475

Max Act: 0.6836. Min Act: -0.0000

Data Index: 1264103 (The Pile)

Max Activating Token Index: 48