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

Dataset: The Pile

Neuron 1008 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: 1.6291. Min Range: -1.6291

Max Act: 1.6291. Min Act: -0.0000

Data Index: 1479717 (The Pile)

Max Activating Token Index: 114

Text #1

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.4347. Min Act: -0.0000

Data Index: 144279 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3465. Min Act: -0.0000

Data Index: 1427505 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3594. Min Act: -0.0000

Data Index: 1872827 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.2231. Min Act: -0.0000

Data Index: 1083970 (The Pile)

Max Activating Token Index: 269

Text #5

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1804889 (The Pile)

Max Activating Token Index: 441

Text #6

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.0508. Min Act: -0.0000

Data Index: 17149 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.0871. Min Act: -0.0000

Data Index: 400241 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1870516 (The Pile)

Max Activating Token Index: 618

Text #9

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.1509. Min Act: -0.0000

Data Index: 196650 (The Pile)

Max Activating Token Index: 536

Text #10

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.1453. Min Act: -0.0000

Data Index: 1623610 (The Pile)

Max Activating Token Index: 992

Text #11

Max Range: 1.6291. Min Range: -1.6291

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1349168 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.9241. Min Act: -0.0000

Data Index: 1135941 (The Pile)

Max Activating Token Index: 41

Text #13

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.9242. Min Act: -0.0000

Data Index: 1745562 (The Pile)

Max Activating Token Index: 312

Text #14

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.9148. Min Act: -0.0000

Data Index: 1394624 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.9022. Min Act: -0.0000

Data Index: 96905 (The Pile)

Max Activating Token Index: 333

Text #16

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.9081. Min Act: -0.0000

Data Index: 120004 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1567217 (The Pile)

Max Activating Token Index: 317

Text #18

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1092318 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 1.6291. Min Range: -1.6291

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1804311 (The Pile)

Max Activating Token Index: 244