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

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

Neuron 1921 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1570. Min Act: -0.0001

Data Index: 374814 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1492. Min Act: -0.0001

Data Index: 827018 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1477. Min Act: -0.0001

Data Index: 953133 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1326. Min Act: -0.0002

Data Index: 32533 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1365. Min Act: -0.0002

Data Index: 1355432 (C4 (Web Text))

Max Activating Token Index: 676

Text #5

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1343. Min Act: -0.0002

Data Index: 1099763 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1305. Min Act: -0.0001

Data Index: 1051525 (C4 (Web Text))

Max Activating Token Index: 306

Text #7

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1264. Min Act: -0.0001

Data Index: 637385 (C4 (Web Text))

Max Activating Token Index: 503

Text #8

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1216. Min Act: -0.0002

Data Index: 514334 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1257. Min Act: -0.0001

Data Index: 322381 (C4 (Web Text))

Max Activating Token Index: 834

Text #10

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1257. Min Act: -0.0002

Data Index: 41355 (C4 (Web Text))

Max Activating Token Index: 25

Text #11

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1182. Min Act: -0.0002

Data Index: 574576 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1160376 (C4 (Web Text))

Max Activating Token Index: 4

Text #13

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1158. Min Act: -0.0001

Data Index: 1336810 (C4 (Web Text))

Max Activating Token Index: 42

Text #14

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1136. Min Act: -0.0001

Data Index: 540932 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1157. Min Act: -0.0001

Data Index: 303445 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1175. Min Act: -0.0001

Data Index: 644664 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1239. Min Act: -0.0001

Data Index: 603602 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1090. Min Act: -0.0002

Data Index: 111183 (C4 (Web Text))

Max Activating Token Index: 183

Text #19

Max Range: 0.1570. Min Range: -0.1570

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1324502 (C4 (Web Text))

Max Activating Token Index: 152