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

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

Neuron 4796 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.2366. Min Act: -0.0000

Data Index: 643200 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1771. Min Act: -0.0000

Data Index: 125172 (C4 (Web Text))

Max Activating Token Index: 115

Text #2

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1176972 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1273. Min Act: -0.0000

Data Index: 59771 (C4 (Web Text))

Max Activating Token Index: 343

Text #4

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1233. Min Act: -0.0000

Data Index: 196736 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1255. Min Act: -0.0000

Data Index: 965369 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1215. Min Act: -0.0000

Data Index: 792935 (C4 (Web Text))

Max Activating Token Index: 370

Text #7

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1182. Min Act: -0.0000

Data Index: 910343 (C4 (Web Text))

Max Activating Token Index: 447

Text #8

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1082483 (C4 (Web Text))

Max Activating Token Index: 509

Text #9

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1193994 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1077. Min Act: -0.0000

Data Index: 833503 (C4 (Web Text))

Max Activating Token Index: 434

Text #11

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1141. Min Act: -0.0000

Data Index: 412632 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1142. Min Act: -0.0000

Data Index: 367674 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1126. Min Act: -0.0000

Data Index: 593718 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1124. Min Act: -0.0000

Data Index: 317117 (C4 (Web Text))

Max Activating Token Index: 665

Text #15

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1122. Min Act: -0.0000

Data Index: 1004939 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1147. Min Act: -0.0000

Data Index: 910649 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1246459 (C4 (Web Text))

Max Activating Token Index: 816

Text #18

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1087. Min Act: -0.0000

Data Index: 206943 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.2366. Min Range: -0.2366

Max Act: 0.1061. Min Act: -0.0000

Data Index: 239162 (C4 (Web Text))

Max Activating Token Index: 939