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

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

Neuron 2587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1219648 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1293. Min Act: -0.0000

Data Index: 1302304 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1280. Min Act: -0.0000

Data Index: 673663 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1278. Min Act: -0.0000

Data Index: 908 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1194. Min Act: -0.0000

Data Index: 1331533 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1262910 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1209. Min Act: -0.0000

Data Index: 369611 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1007273 (C4 (Web Text))

Max Activating Token Index: 896

Text #8

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1111. Min Act: -0.0000

Data Index: 522298 (C4 (Web Text))

Max Activating Token Index: 280

Text #9

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1190931 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1047. Min Act: -0.0000

Data Index: 325964 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1162. Min Act: -0.0000

Data Index: 1201458 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1090. Min Act: -0.0000

Data Index: 572804 (C4 (Web Text))

Max Activating Token Index: 134

Text #13

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1083. Min Act: -0.0000

Data Index: 320075 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1039. Min Act: -0.0000

Data Index: 1159367 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1042. Min Act: -0.0000

Data Index: 501414 (C4 (Web Text))

Max Activating Token Index: 891

Text #16

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1072. Min Act: -0.0000

Data Index: 193710 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1030. Min Act: -0.0000

Data Index: 214078 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1058. Min Act: -0.0000

Data Index: 612105 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.1468. Min Range: -0.1468

Max Act: 0.1062. Min Act: -0.0000

Data Index: 108205 (C4 (Web Text))

Max Activating Token Index: 679