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

Dataset: The Pile

Neuron 2875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.1301. Min Range: -1.1301

Max Act: 1.1301. Min Act: -0.0000

Data Index: 1035946 (The Pile)

Max Activating Token Index: 743

Text #1

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1999923 (The Pile)

Max Activating Token Index: 36

Text #2

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9375. Min Act: -0.0000

Data Index: 861528 (The Pile)

Max Activating Token Index: 863

Text #3

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9208. Min Act: -0.0000

Data Index: 1335738 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1476219 (The Pile)

Max Activating Token Index: 162

Text #5

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9346. Min Act: -0.0000

Data Index: 282638 (The Pile)

Max Activating Token Index: 384

Text #6

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9297. Min Act: -0.0000

Data Index: 1336945 (The Pile)

Max Activating Token Index: 490

Text #7

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1605107 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8982. Min Act: -0.0000

Data Index: 1858139 (The Pile)

Max Activating Token Index: 38

Text #9

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9286. Min Act: -0.0000

Data Index: 88889 (The Pile)

Max Activating Token Index: 181

Text #10

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1440029 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9432. Min Act: -0.0000

Data Index: 284911 (The Pile)

Max Activating Token Index: 186

Text #12

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8897. Min Act: -0.0000

Data Index: 621102 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9033. Min Act: -0.0000

Data Index: 907303 (The Pile)

Max Activating Token Index: 168

Text #14

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1637991 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8677. Min Act: -0.0000

Data Index: 787661 (The Pile)

Max Activating Token Index: 229

Text #16

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8702. Min Act: -0.0000

Data Index: 636911 (The Pile)

Max Activating Token Index: 667

Text #17

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.9123. Min Act: -0.0000

Data Index: 482752 (The Pile)

Max Activating Token Index: 101

Text #18

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1103858 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 1.1301. Min Range: -1.1301

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1282456 (The Pile)

Max Activating Token Index: 231