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

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

Neuron 3886 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1571. Min Act: -0.0001

Data Index: 128228 (C4 (Web Text))

Max Activating Token Index: 297

Text #1

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1540. Min Act: -0.0001

Data Index: 667237 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1518. Min Act: -0.0001

Data Index: 215863 (C4 (Web Text))

Max Activating Token Index: 433

Text #3

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1460. Min Act: -0.0001

Data Index: 26042 (C4 (Web Text))

Max Activating Token Index: 162

Text #4

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1015106 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1396. Min Act: -0.0001

Data Index: 693533 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1387. Min Act: -0.0001

Data Index: 1327022 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1485. Min Act: -0.0000

Data Index: 482137 (C4 (Web Text))

Max Activating Token Index: 334

Text #8

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1384. Min Act: -0.0001

Data Index: 571577 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1052637 (C4 (Web Text))

Max Activating Token Index: 422

Text #10

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1368. Min Act: -0.0001

Data Index: 726491 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1344022 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1348. Min Act: -0.0001

Data Index: 517547 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1288. Min Act: -0.0001

Data Index: 421691 (C4 (Web Text))

Max Activating Token Index: 736

Text #14

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1285. Min Act: -0.0001

Data Index: 430433 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1293. Min Act: -0.0001

Data Index: 438082 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1193. Min Act: -0.0001

Data Index: 471727 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1132900 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1263. Min Act: -0.0001

Data Index: 286301 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.1571. Min Range: -0.1571

Max Act: 0.1260. Min Act: -0.0001

Data Index: 195520 (C4 (Web Text))

Max Activating Token Index: 1008