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

Dataset: The Pile

Neuron 2685 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: 1.0835. Min Range: -1.0835

Max Act: 1.0835. Min Act: -0.0000

Data Index: 1245588 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1830604 (The Pile)

Max Activating Token Index: 852

Text #2

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.8215. Min Act: -0.0000

Data Index: 988480 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.7186. Min Act: -0.0000

Data Index: 190010 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.6641. Min Act: -0.0000

Data Index: 264805 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.6598. Min Act: -0.0000

Data Index: 224938 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.6540. Min Act: -0.0000

Data Index: 427400 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.6179. Min Act: -0.0000

Data Index: 1391582 (The Pile)

Max Activating Token Index: 584

Text #8

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.6282. Min Act: -0.0000

Data Index: 1360578 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1359956 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.5767. Min Act: -0.0000

Data Index: 1970701 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.5396. Min Act: -0.0000

Data Index: 302555 (The Pile)

Max Activating Token Index: 314

Text #12

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.5783. Min Act: -0.0000

Data Index: 930629 (The Pile)

Max Activating Token Index: 478

Text #13

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1628654 (The Pile)

Max Activating Token Index: 317

Text #14

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.6074. Min Act: -0.0000

Data Index: 684495 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.4976. Min Act: -0.0000

Data Index: 63305 (The Pile)

Max Activating Token Index: 646

Text #16

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.5309. Min Act: -0.0000

Data Index: 274230 (The Pile)

Max Activating Token Index: 540

Text #17

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.5598. Min Act: -0.0000

Data Index: 1371150 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.4676. Min Act: -0.0000

Data Index: 1164378 (The Pile)

Max Activating Token Index: 729

Text #19

Max Range: 1.0835. Min Range: -1.0835

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1224307 (The Pile)

Max Activating Token Index: 401