Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 40 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0001

Data Index: 934846 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1184. Min Act: -0.0001

Data Index: 289516 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1296. Min Act: -0.0001

Data Index: 646114 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1266. Min Act: -0.0001

Data Index: 767315 (C4 (Web Text))

Max Activating Token Index: 290

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1054. Min Act: -0.0001

Data Index: 1252490 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1320. Min Act: -0.0001

Data Index: 1120226 (C4 (Web Text))

Max Activating Token Index: 809

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1244. Min Act: -0.0001

Data Index: 942535 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1360. Min Act: -0.0001

Data Index: 302020 (C4 (Web Text))

Max Activating Token Index: 300

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1151. Min Act: -0.0001

Data Index: 1064595 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1181. Min Act: -0.0001

Data Index: 922607 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1090323 (C4 (Web Text))

Max Activating Token Index: 661

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1189293 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1086. Min Act: -0.0001

Data Index: 313758 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1019. Min Act: -0.0001

Data Index: 367201 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1081. Min Act: -0.0001

Data Index: 549803 (C4 (Web Text))

Max Activating Token Index: 727

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1045. Min Act: -0.0001

Data Index: 526934 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1035576 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0892. Min Act: -0.0001

Data Index: 660374 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0954. Min Act: -0.0001

Data Index: 1101134 (C4 (Web Text))

Max Activating Token Index: 616

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.0925. Min Act: -0.0001

Data Index: 435766 (C4 (Web Text))

Max Activating Token Index: 112