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

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

Neuron 1164 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0001

Data Index: 714571 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1506. Min Act: -0.0001

Data Index: 826655 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1497. Min Act: -0.0001

Data Index: 143020 (C4 (Web Text))

Max Activating Token Index: 927

Text #3

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1385. Min Act: -0.0001

Data Index: 385248 (C4 (Web Text))

Max Activating Token Index: 218

Text #4

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1377. Min Act: -0.0001

Data Index: 930828 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1294. Min Act: -0.0001

Data Index: 1302545 (C4 (Web Text))

Max Activating Token Index: 544

Text #6

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1118381 (C4 (Web Text))

Max Activating Token Index: 212

Text #7

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1316. Min Act: -0.0001

Data Index: 225740 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1356. Min Act: -0.0001

Data Index: 763200 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1309. Min Act: -0.0001

Data Index: 311599 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1361. Min Act: -0.0001

Data Index: 470239 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1393. Min Act: -0.0001

Data Index: 883999 (C4 (Web Text))

Max Activating Token Index: 833

Text #12

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1341. Min Act: -0.0001

Data Index: 1313584 (C4 (Web Text))

Max Activating Token Index: 189

Text #13

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1203. Min Act: -0.0001

Data Index: 800172 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1233520 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1228. Min Act: -0.0001

Data Index: 387171 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1270. Min Act: -0.0001

Data Index: 447120 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1033781 (C4 (Web Text))

Max Activating Token Index: 710

Text #18

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1164. Min Act: -0.0001

Data Index: 938395 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1112. Min Act: -0.0001

Data Index: 1345575 (C4 (Web Text))

Max Activating Token Index: 995