Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 782 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1445. Min Act: -0.0002

Data Index: 1227523 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1430. Min Act: -0.0002

Data Index: 715128 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1428. Min Act: -0.0002

Data Index: 1100326 (C4 (Web Text))

Max Activating Token Index: 117

Text #3

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1426. Min Act: -0.0002

Data Index: 1007877 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1407. Min Act: -0.0002

Data Index: 735291 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1375. Min Act: -0.0002

Data Index: 1013913 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1359. Min Act: -0.0002

Data Index: 139709 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1342. Min Act: -0.0002

Data Index: 844176 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1267. Min Act: -0.0002

Data Index: 1041075 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1305. Min Act: -0.0002

Data Index: 594233 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1288. Min Act: -0.0002

Data Index: 442368 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1287. Min Act: -0.0002

Data Index: 907156 (C4 (Web Text))

Max Activating Token Index: 43

Text #12

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1276. Min Act: -0.0002

Data Index: 1345525 (C4 (Web Text))

Max Activating Token Index: 70

Text #13

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1260. Min Act: -0.0002

Data Index: 804967 (C4 (Web Text))

Max Activating Token Index: 291

Text #14

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1306. Min Act: -0.0002

Data Index: 1203637 (C4 (Web Text))

Max Activating Token Index: 417

Text #15

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1247. Min Act: -0.0002

Data Index: 216224 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1243. Min Act: -0.0002

Data Index: 1204287 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1232. Min Act: -0.0002

Data Index: 617873 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1217. Min Act: -0.0002

Data Index: 1167363 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 0.1445. Min Range: -0.1445

Max Act: 0.1214. Min Act: -0.0002

Data Index: 772880 (C4 (Web Text))

Max Activating Token Index: 72