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

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

Neuron 4775 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1394. Min Act: -0.0001

Data Index: 343098 (C4 (Web Text))

Max Activating Token Index: 433

Text #1

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1308. Min Act: -0.0000

Data Index: 460050 (C4 (Web Text))

Max Activating Token Index: 450

Text #2

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1190. Min Act: -0.0001

Data Index: 498266 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1090. Min Act: -0.0001

Data Index: 445731 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1038021 (C4 (Web Text))

Max Activating Token Index: 475

Text #5

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1111. Min Act: -0.0001

Data Index: 1136888 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1144. Min Act: -0.0001

Data Index: 225691 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1109. Min Act: -0.0001

Data Index: 742124 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1164. Min Act: -0.0001

Data Index: 567401 (C4 (Web Text))

Max Activating Token Index: 817

Text #9

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1046. Min Act: -0.0001

Data Index: 149581 (C4 (Web Text))

Max Activating Token Index: 120

Text #10

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1167. Min Act: -0.0001

Data Index: 558514 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1104253 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1005555 (C4 (Web Text))

Max Activating Token Index: 346

Text #13

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1093. Min Act: -0.0001

Data Index: 1308283 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1086. Min Act: -0.0001

Data Index: 632526 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1109. Min Act: -0.0001

Data Index: 1200556 (C4 (Web Text))

Max Activating Token Index: 199

Text #16

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1167329 (C4 (Web Text))

Max Activating Token Index: 452

Text #17

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1100. Min Act: -0.0001

Data Index: 865571 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1013. Min Act: -0.0001

Data Index: 146745 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1394. Min Range: -0.1394

Max Act: 0.1046. Min Act: -0.0001

Data Index: 707899 (C4 (Web Text))

Max Activating Token Index: 730