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

Dataset: The Pile

Neuron 1158 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: 1.4812. Min Range: -1.4812

Max Act: 1.4576. Min Act: -0.0000

Data Index: 887599 (The Pile)

Max Activating Token Index: 816

Text #1

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.4812. Min Act: -0.0000

Data Index: 504116 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2340. Min Act: -0.0000

Data Index: 1621552 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2690. Min Act: -0.0000

Data Index: 668946 (The Pile)

Max Activating Token Index: 906

Text #4

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1399. Min Act: -0.0000

Data Index: 1561264 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2996. Min Act: -0.0000

Data Index: 1720031 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2460. Min Act: -0.0000

Data Index: 1853166 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2414. Min Act: -0.0000

Data Index: 211320 (The Pile)

Max Activating Token Index: 383

Text #8

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1159. Min Act: -0.0000

Data Index: 1356068 (The Pile)

Max Activating Token Index: 168

Text #9

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2304. Min Act: -0.0000

Data Index: 1030671 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1773. Min Act: -0.0000

Data Index: 387799 (The Pile)

Max Activating Token Index: 468

Text #11

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1401. Min Act: -0.0000

Data Index: 666512 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1761. Min Act: -0.0000

Data Index: 1765497 (The Pile)

Max Activating Token Index: 25

Text #13

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1817. Min Act: -0.0000

Data Index: 1563190 (The Pile)

Max Activating Token Index: 195

Text #14

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2208. Min Act: -0.0000

Data Index: 959307 (The Pile)

Max Activating Token Index: 669

Text #15

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.0448. Min Act: -0.0000

Data Index: 1749564 (The Pile)

Max Activating Token Index: 174

Text #16

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.2001. Min Act: -0.0000

Data Index: 886833 (The Pile)

Max Activating Token Index: 567

Text #17

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1287. Min Act: -0.0000

Data Index: 140914 (The Pile)

Max Activating Token Index: 424

Text #18

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1391824 (The Pile)

Max Activating Token Index: 980

Text #19

Max Range: 1.4812. Min Range: -1.4812

Max Act: 1.1422. Min Act: -0.0000

Data Index: 1446860 (The Pile)

Max Activating Token Index: 62