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

Dataset: The Pile

Neuron 761 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1965. Min Act: -0.0000

Data Index: 1065113 (The Pile)

Max Activating Token Index: 884

Text #1

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2085. Min Act: -0.0000

Data Index: 688457 (The Pile)

Max Activating Token Index: 937

Text #2

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2465. Min Act: -0.0000

Data Index: 1609971 (The Pile)

Max Activating Token Index: 809

Text #3

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2980. Min Act: -0.0000

Data Index: 1930558 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2158. Min Act: -0.0000

Data Index: 1475879 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2835. Min Act: -0.0000

Data Index: 463652 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2031. Min Act: -0.0000

Data Index: 701891 (The Pile)

Max Activating Token Index: 941

Text #7

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.2012. Min Act: -0.0000

Data Index: 364322 (The Pile)

Max Activating Token Index: 223

Text #8

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1597. Min Act: -0.0000

Data Index: 196847 (The Pile)

Max Activating Token Index: 449

Text #9

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1290059 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1006. Min Act: -0.0000

Data Index: 291441 (The Pile)

Max Activating Token Index: 752

Text #11

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1436. Min Act: -0.0000

Data Index: 747043 (The Pile)

Max Activating Token Index: 183

Text #12

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1078646 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9637. Min Act: -0.0000

Data Index: 1984709 (The Pile)

Max Activating Token Index: 886

Text #14

Max Range: 1.2980. Min Range: -1.2980

Max Act: 0.9957. Min Act: -0.0000

Data Index: 168750 (The Pile)

Max Activating Token Index: 838

Text #15

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0797. Min Act: -0.0000

Data Index: 1390935 (The Pile)

Max Activating Token Index: 472

Text #16

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1067. Min Act: -0.0000

Data Index: 1854561 (The Pile)

Max Activating Token Index: 601

Text #17

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1126. Min Act: -0.0000

Data Index: 133335 (The Pile)

Max Activating Token Index: 467

Text #18

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.0496. Min Act: -0.0000

Data Index: 628359 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 1.2980. Min Range: -1.2980

Max Act: 1.1177. Min Act: -0.0000

Data Index: 1791439 (The Pile)

Max Activating Token Index: 956