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

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

Neuron 558 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1569. Min Act: -0.0003

Data Index: 906790 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1340. Min Act: -0.0003

Data Index: 608580 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1314. Min Act: -0.0003

Data Index: 927378 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1345. Min Act: -0.0003

Data Index: 342234 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1368. Min Act: -0.0003

Data Index: 1103687 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1281. Min Act: -0.0003

Data Index: 1190061 (C4 (Web Text))

Max Activating Token Index: 785

Text #6

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1157. Min Act: -0.0003

Data Index: 647660 (C4 (Web Text))

Max Activating Token Index: 761

Text #7

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1280. Min Act: -0.0003

Data Index: 732171 (C4 (Web Text))

Max Activating Token Index: 881

Text #8

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1311. Min Act: -0.0003

Data Index: 1289985 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1276. Min Act: -0.0003

Data Index: 411258 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1403. Min Act: -0.0003

Data Index: 523659 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1238. Min Act: -0.0003

Data Index: 1445121 (Python Code)

Max Activating Token Index: 803

Text #12

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1326. Min Act: -0.0003

Data Index: 202018 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.0965. Min Act: -0.0003

Data Index: 667879 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1201. Min Act: -0.0003

Data Index: 522115 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1103. Min Act: -0.0003

Data Index: 163791 (C4 (Web Text))

Max Activating Token Index: 502

Text #16

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1148. Min Act: -0.0003

Data Index: 1256478 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1195. Min Act: -0.0003

Data Index: 29642 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1227. Min Act: -0.0003

Data Index: 901021 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 0.1569. Min Range: -0.1569

Max Act: 0.1174. Min Act: -0.0003

Data Index: 357858 (C4 (Web Text))

Max Activating Token Index: 68