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

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

Neuron 1433 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: 0.1507. Min Range: -0.1507

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1298533 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1507. Min Act: -0.0001

Data Index: 870211 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1501. Min Act: -0.0001

Data Index: 142334 (C4 (Web Text))

Max Activating Token Index: 960

Text #3

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1424. Min Act: -0.0001

Data Index: 614358 (C4 (Web Text))

Max Activating Token Index: 909

Text #4

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1122957 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1394. Min Act: -0.0001

Data Index: 459742 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1176135 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1285. Min Act: -0.0001

Data Index: 206339 (C4 (Web Text))

Max Activating Token Index: 740

Text #8

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1274. Min Act: -0.0001

Data Index: 544121 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1255. Min Act: -0.0001

Data Index: 1323402 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1299. Min Act: -0.0001

Data Index: 55904 (C4 (Web Text))

Max Activating Token Index: 112

Text #11

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1243. Min Act: -0.0001

Data Index: 532696 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1278. Min Act: -0.0001

Data Index: 1040000 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1268. Min Act: -0.0001

Data Index: 446324 (C4 (Web Text))

Max Activating Token Index: 927

Text #14

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1176. Min Act: -0.0001

Data Index: 716037 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1201. Min Act: -0.0000

Data Index: 459420 (C4 (Web Text))

Max Activating Token Index: 879

Text #16

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1136. Min Act: -0.0001

Data Index: 302066 (C4 (Web Text))

Max Activating Token Index: 207

Text #17

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1178. Min Act: -0.0001

Data Index: 718827 (C4 (Web Text))

Max Activating Token Index: 942

Text #18

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1170. Min Act: -0.0001

Data Index: 357069 (C4 (Web Text))

Max Activating Token Index: 217

Text #19

Max Range: 0.1507. Min Range: -0.1507

Max Act: 0.1164. Min Act: -0.0001

Data Index: 1271309 (C4 (Web Text))

Max Activating Token Index: 818