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

Dataset: The Pile

Neuron 78 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: 0.7835. Min Range: -0.7835

Max Act: 0.7835. Min Act: -0.0000

Data Index: 1076763 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5980. Min Act: -0.0000

Data Index: 1811008 (The Pile)

Max Activating Token Index: 332

Text #2

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5960. Min Act: -0.0000

Data Index: 679896 (The Pile)

Max Activating Token Index: 546

Text #3

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.6096. Min Act: -0.0000

Data Index: 342821 (The Pile)

Max Activating Token Index: 56

Text #4

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5790. Min Act: -0.0000

Data Index: 745224 (The Pile)

Max Activating Token Index: 584

Text #5

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5724. Min Act: -0.0000

Data Index: 1782882 (The Pile)

Max Activating Token Index: 466

Text #6

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5622. Min Act: -0.0000

Data Index: 476435 (The Pile)

Max Activating Token Index: 592

Text #7

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5260. Min Act: -0.0000

Data Index: 172740 (The Pile)

Max Activating Token Index: 61

Text #8

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5439. Min Act: -0.0000

Data Index: 364328 (The Pile)

Max Activating Token Index: 198

Text #9

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1590661 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5471. Min Act: -0.0000

Data Index: 207810 (The Pile)

Max Activating Token Index: 53

Text #11

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5540. Min Act: -0.0000

Data Index: 1656832 (The Pile)

Max Activating Token Index: 864

Text #12

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1435372 (The Pile)

Max Activating Token Index: 352

Text #13

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5084. Min Act: -0.0000

Data Index: 413397 (The Pile)

Max Activating Token Index: 836

Text #14

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5218. Min Act: -0.0000

Data Index: 977060 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5399. Min Act: -0.0000

Data Index: 1312427 (The Pile)

Max Activating Token Index: 43

Text #16

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1317334 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5146. Min Act: -0.0000

Data Index: 1426530 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5144. Min Act: -0.0000

Data Index: 926528 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.7835. Min Range: -0.7835

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1479651 (The Pile)

Max Activating Token Index: 459