Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0001

Data Index: 407496 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1190819 (C4 (Web Text))

Max Activating Token Index: 561

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1307629 (C4 (Web Text))

Max Activating Token Index: 841

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1422. Min Act: -0.0001

Data Index: 671568 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1225. Min Act: -0.0001

Data Index: 1066575 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1343597 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1265. Min Act: -0.0001

Data Index: 1160628 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1282. Min Act: -0.0001

Data Index: 419814 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1274. Min Act: -0.0001

Data Index: 728239 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1256. Min Act: -0.0001

Data Index: 403366 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1179. Min Act: -0.0001

Data Index: 1315989 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1128. Min Act: -0.0001

Data Index: 151302 (C4 (Web Text))

Max Activating Token Index: 922

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1151. Min Act: -0.0001

Data Index: 653237 (C4 (Web Text))

Max Activating Token Index: 111

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1188. Min Act: -0.0001

Data Index: 4814 (C4 (Web Text))

Max Activating Token Index: 968

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1199. Min Act: -0.0001

Data Index: 963291 (C4 (Web Text))

Max Activating Token Index: 242

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1145. Min Act: -0.0001

Data Index: 218977 (C4 (Web Text))

Max Activating Token Index: 749

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1177. Min Act: -0.0001

Data Index: 470178 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1023. Min Act: -0.0001

Data Index: 381341 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1115. Min Act: -0.0001

Data Index: 241069 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1151. Min Act: -0.0001

Data Index: 913740 (C4 (Web Text))

Max Activating Token Index: 636