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

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

Neuron 321 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1726. Min Act: -0.0001

Data Index: 208940 (C4 (Web Text))

Max Activating Token Index: 894

Text #1

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1464. Min Act: -0.0000

Data Index: 125064 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1374. Min Act: -0.0001

Data Index: 1277327 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1117807 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1304. Min Act: -0.0000

Data Index: 545518 (C4 (Web Text))

Max Activating Token Index: 495

Text #5

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1278. Min Act: -0.0001

Data Index: 460042 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1266. Min Act: -0.0001

Data Index: 414704 (C4 (Web Text))

Max Activating Token Index: 380

Text #7

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1195. Min Act: -0.0000

Data Index: 735300 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1220. Min Act: 0.0000

Data Index: 651853 (C4 (Web Text))

Max Activating Token Index: 95

Text #9

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1211. Min Act: -0.0001

Data Index: 1057861 (C4 (Web Text))

Max Activating Token Index: 361

Text #10

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1176. Min Act: -0.0001

Data Index: 858951 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1170. Min Act: -0.0000

Data Index: 512723 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1250471 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1108. Min Act: -0.0001

Data Index: 911869 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1105. Min Act: -0.0000

Data Index: 680766 (C4 (Web Text))

Max Activating Token Index: 846

Text #15

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1163. Min Act: -0.0000

Data Index: 698510 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1102. Min Act: -0.0000

Data Index: 299 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1180. Min Act: -0.0000

Data Index: 212382 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1134. Min Act: -0.0001

Data Index: 587559 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.1726. Min Range: -0.1726

Max Act: 0.1088. Min Act: -0.0001

Data Index: 969248 (C4 (Web Text))

Max Activating Token Index: 746