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

Dataset: The Pile

Neuron 2882 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: 1.4443. Min Range: -1.4443

Max Act: 1.4443. Min Act: -0.0000

Data Index: 1026899 (The Pile)

Max Activating Token Index: 389

Text #1

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3281. Min Act: -0.0000

Data Index: 1833258 (The Pile)

Max Activating Token Index: 209

Text #2

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.2419. Min Act: -0.0000

Data Index: 330717 (The Pile)

Max Activating Token Index: 150

Text #3

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.3069. Min Act: 0.0000

Data Index: 1338053 (The Pile)

Max Activating Token Index: 108

Text #4

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.2320. Min Act: -0.0000

Data Index: 994194 (The Pile)

Max Activating Token Index: 510

Text #5

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.2211. Min Act: -0.0000

Data Index: 1299159 (The Pile)

Max Activating Token Index: 645

Text #6

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1781. Min Act: -0.0000

Data Index: 214884 (The Pile)

Max Activating Token Index: 373

Text #7

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1723. Min Act: -0.0000

Data Index: 359648 (The Pile)

Max Activating Token Index: 689

Text #8

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.1886. Min Act: 0.0000

Data Index: 1604543 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0230. Min Act: 0.0000

Data Index: 1586845 (The Pile)

Max Activating Token Index: 944

Text #10

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0170. Min Act: 0.0000

Data Index: 1047799 (The Pile)

Max Activating Token Index: 160

Text #11

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9864. Min Act: -0.0000

Data Index: 1813971 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1832149 (The Pile)

Max Activating Token Index: 1012

Text #13

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9491. Min Act: 0.0000

Data Index: 282761 (The Pile)

Max Activating Token Index: 840

Text #14

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0319. Min Act: 0.0000

Data Index: 1120469 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0298. Min Act: -0.0000

Data Index: 187798 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 1.4443. Min Range: -1.4443

Max Act: 0.9706. Min Act: 0.0000

Data Index: 717545 (The Pile)

Max Activating Token Index: 624

Text #17

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0324. Min Act: -0.0000

Data Index: 374711 (The Pile)

Max Activating Token Index: 478

Text #18

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0283. Min Act: -0.0000

Data Index: 357920 (The Pile)

Max Activating Token Index: 49

Text #19

Max Range: 1.4443. Min Range: -1.4443

Max Act: 1.0194. Min Act: -0.0000

Data Index: 1330544 (The Pile)

Max Activating Token Index: 97