Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 3027 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1691382 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1511. Min Act: -0.0000

Data Index: 967113 (The Pile)

Max Activating Token Index: 791

Text #2

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1402. Min Act: -0.0000

Data Index: 396509 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1333. Min Act: -0.0000

Data Index: 1281773 (The Pile)

Max Activating Token Index: 399

Text #4

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1348. Min Act: -0.0000

Data Index: 1492268 (The Pile)

Max Activating Token Index: 378

Text #5

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1294. Min Act: -0.0000

Data Index: 454280 (The Pile)

Max Activating Token Index: 369

Text #6

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1289. Min Act: -0.0000

Data Index: 409273 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1230. Min Act: -0.0000

Data Index: 483699 (The Pile)

Max Activating Token Index: 193

Text #8

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1190. Min Act: -0.0000

Data Index: 29066 (The Pile)

Max Activating Token Index: 377

Text #9

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1646059 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1167. Min Act: -0.0000

Data Index: 788381 (The Pile)

Max Activating Token Index: 628

Text #11

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1109. Min Act: -0.0000

Data Index: 292252 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1080. Min Act: -0.0000

Data Index: 641397 (The Pile)

Max Activating Token Index: 724

Text #13

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1072. Min Act: -0.0000

Data Index: 1155490 (The Pile)

Max Activating Token Index: 696

Text #14

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1110. Min Act: -0.0000

Data Index: 250479 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1422401 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1060. Min Act: -0.0000

Data Index: 822384 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1092. Min Act: -0.0000

Data Index: 507709 (The Pile)

Max Activating Token Index: 719

Text #18

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1091. Min Act: -0.0000

Data Index: 1838203 (The Pile)

Max Activating Token Index: 265

Text #19

Max Range: 0.1511. Min Range: -0.1511

Max Act: 0.1068. Min Act: -0.0000

Data Index: 355678 (The Pile)

Max Activating Token Index: 710