Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 858 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1789. Min Act: -0.0001

Data Index: 190367 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1841. Min Act: -0.0001

Data Index: 546420 (C4 (Web Text))

Max Activating Token Index: 813

Text #2

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1315. Min Act: -0.0000

Data Index: 802740 (C4 (Web Text))

Max Activating Token Index: 501

Text #3

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1300. Min Act: 0.0000

Data Index: 921254 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1295. Min Act: -0.0001

Data Index: 560375 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1264669 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1106. Min Act: -0.0000

Data Index: 82074 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1007332 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1080. Min Act: 0.0000

Data Index: 60577 (C4 (Web Text))

Max Activating Token Index: 103

Text #9

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1062. Min Act: -0.0001

Data Index: 273379 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1062. Min Act: -0.0000

Data Index: 773317 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1096. Min Act: -0.0000

Data Index: 963387 (C4 (Web Text))

Max Activating Token Index: 887

Text #12

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1056. Min Act: -0.0000

Data Index: 50406 (C4 (Web Text))

Max Activating Token Index: 828

Text #13

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1040. Min Act: -0.0000

Data Index: 221839 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.1049. Min Act: -0.0000

Data Index: 322414 (C4 (Web Text))

Max Activating Token Index: 302

Text #15

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.0999. Min Act: -0.0001

Data Index: 21775 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.0996. Min Act: -0.0000

Data Index: 901698 (C4 (Web Text))

Max Activating Token Index: 309

Text #17

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1127358 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.0987. Min Act: -0.0000

Data Index: 406350 (C4 (Web Text))

Max Activating Token Index: 292

Text #19

Max Range: 0.1841. Min Range: -0.1841

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1323114 (C4 (Web Text))

Max Activating Token Index: 878