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

Dataset: The Pile

Neuron 2909 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: 1.2163. Min Range: -1.2163

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1731931 (The Pile)

Max Activating Token Index: 316

Text #1

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.1437. Min Act: -0.0000

Data Index: 1846466 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.0537. Min Act: -0.0000

Data Index: 795601 (The Pile)

Max Activating Token Index: 314

Text #3

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.0984. Min Act: -0.0000

Data Index: 511744 (The Pile)

Max Activating Token Index: 999

Text #4

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.1227. Min Act: -0.0000

Data Index: 679535 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.1003. Min Act: -0.0000

Data Index: 524585 (The Pile)

Max Activating Token Index: 891

Text #6

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9991. Min Act: -0.0000

Data Index: 69093 (The Pile)

Max Activating Token Index: 299

Text #7

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9642. Min Act: -0.0000

Data Index: 1274881 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9805. Min Act: -0.0000

Data Index: 447394 (The Pile)

Max Activating Token Index: 258

Text #9

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9984. Min Act: -0.0000

Data Index: 1252129 (The Pile)

Max Activating Token Index: 255

Text #10

Max Range: 1.2163. Min Range: -1.2163

Max Act: 1.0163. Min Act: -0.0000

Data Index: 220995 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9433. Min Act: -0.0000

Data Index: 883548 (The Pile)

Max Activating Token Index: 847

Text #12

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8353. Min Act: -0.0000

Data Index: 762777 (The Pile)

Max Activating Token Index: 709

Text #13

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9421. Min Act: -0.0000

Data Index: 404968 (The Pile)

Max Activating Token Index: 735

Text #14

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9719. Min Act: -0.0000

Data Index: 1051846 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1845999 (The Pile)

Max Activating Token Index: 625

Text #16

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8783. Min Act: -0.0000

Data Index: 5779 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8999. Min Act: -0.0000

Data Index: 1772614 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8909. Min Act: -0.0000

Data Index: 449427 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 1.2163. Min Range: -1.2163

Max Act: 0.8677. Min Act: -0.0000

Data Index: 1796050 (The Pile)

Max Activating Token Index: 902