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

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

Neuron 3991 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1052021 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1069604 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1549. Min Act: -0.0000

Data Index: 158294 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1467. Min Act: -0.0001

Data Index: 577217 (C4 (Web Text))

Max Activating Token Index: 861

Text #4

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1493. Min Act: -0.0000

Data Index: 734579 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1416. Min Act: -0.0001

Data Index: 700469 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1269086 (C4 (Web Text))

Max Activating Token Index: 139

Text #7

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1420. Min Act: -0.0001

Data Index: 644034 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1358. Min Act: -0.0000

Data Index: 410301 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1403. Min Act: -0.0001

Data Index: 1210573 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1324. Min Act: -0.0001

Data Index: 1186086 (C4 (Web Text))

Max Activating Token Index: 594

Text #11

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1269. Min Act: -0.0000

Data Index: 707149 (C4 (Web Text))

Max Activating Token Index: 815

Text #12

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1349. Min Act: -0.0001

Data Index: 1252787 (C4 (Web Text))

Max Activating Token Index: 964

Text #13

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1263. Min Act: -0.0000

Data Index: 272289 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1283. Min Act: -0.0000

Data Index: 150875 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1230. Min Act: -0.0001

Data Index: 394963 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1321. Min Act: -0.0000

Data Index: 845474 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1316. Min Act: -0.0000

Data Index: 961611 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1302. Min Act: -0.0000

Data Index: 916249 (C4 (Web Text))

Max Activating Token Index: 373

Text #19

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1276. Min Act: -0.0001

Data Index: 478826 (C4 (Web Text))

Max Activating Token Index: 424