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

Dataset: The Pile

Neuron 433 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: 0.2770. Min Range: -0.2770

Max Act: 0.2770. Min Act: -0.0000

Data Index: 869208 (The Pile)

Max Activating Token Index: 559

Text #1

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2484. Min Act: -0.0000

Data Index: 1353230 (The Pile)

Max Activating Token Index: 250

Text #2

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2494. Min Act: -0.0000

Data Index: 877112 (The Pile)

Max Activating Token Index: 66

Text #3

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2536. Min Act: -0.0000

Data Index: 1593080 (The Pile)

Max Activating Token Index: 662

Text #4

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1608114 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2466. Min Act: -0.0000

Data Index: 518313 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2368. Min Act: -0.0000

Data Index: 123913 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2425. Min Act: -0.0000

Data Index: 35782 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2128. Min Act: -0.0000

Data Index: 238072 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2217. Min Act: -0.0000

Data Index: 944159 (The Pile)

Max Activating Token Index: 803

Text #10

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2270. Min Act: -0.0000

Data Index: 747103 (The Pile)

Max Activating Token Index: 618

Text #11

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2316. Min Act: -0.0000

Data Index: 272966 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1359368 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1095824 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2069. Min Act: -0.0000

Data Index: 941781 (The Pile)

Max Activating Token Index: 253

Text #15

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1986. Min Act: -0.0000

Data Index: 636760 (The Pile)

Max Activating Token Index: 284

Text #16

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1108547 (The Pile)

Max Activating Token Index: 387

Text #17

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1941. Min Act: -0.0000

Data Index: 55080 (The Pile)

Max Activating Token Index: 51

Text #18

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1878. Min Act: -0.0000

Data Index: 397750 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 0.2770. Min Range: -0.2770

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1271326 (The Pile)

Max Activating Token Index: 282