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

Dataset: The Pile

Neuron 2711 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: 1.4886. Min Range: -1.4886

Max Act: 1.4886. Min Act: -0.0000

Data Index: 1226268 (The Pile)

Max Activating Token Index: 466

Text #1

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1293. Min Act: -0.0000

Data Index: 1734967 (The Pile)

Max Activating Token Index: 116

Text #2

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1206. Min Act: -0.0000

Data Index: 880996 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1479212 (The Pile)

Max Activating Token Index: 482

Text #4

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0514. Min Act: -0.0000

Data Index: 488414 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1961. Min Act: -0.0000

Data Index: 1297609 (The Pile)

Max Activating Token Index: 551

Text #6

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9205. Min Act: -0.0000

Data Index: 493927 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.2025. Min Act: -0.0000

Data Index: 1852144 (The Pile)

Max Activating Token Index: 214

Text #8

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0360. Min Act: -0.0000

Data Index: 556895 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0014. Min Act: -0.0000

Data Index: 1646306 (The Pile)

Max Activating Token Index: 433

Text #10

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9861. Min Act: -0.0000

Data Index: 768322 (The Pile)

Max Activating Token Index: 145

Text #11

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9951. Min Act: -0.0000

Data Index: 297621 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.1307. Min Act: -0.0000

Data Index: 1853874 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9486. Min Act: -0.0000

Data Index: 832221 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 1.4886. Min Range: -1.4886

Max Act: 1.0080. Min Act: -0.0000

Data Index: 1512884 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9473. Min Act: -0.0000

Data Index: 1438131 (The Pile)

Max Activating Token Index: 459

Text #16

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.8956. Min Act: -0.0000

Data Index: 1402037 (The Pile)

Max Activating Token Index: 351

Text #17

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1301502 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9208. Min Act: -0.0000

Data Index: 478501 (The Pile)

Max Activating Token Index: 497

Text #19

Max Range: 1.4886. Min Range: -1.4886

Max Act: 0.9355. Min Act: -0.0000

Data Index: 1950777 (The Pile)

Max Activating Token Index: 574