Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4152 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1605. Min Act: -0.0001

Data Index: 149813 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1416. Min Act: -0.0001

Data Index: 434750 (C4 (Web Text))

Max Activating Token Index: 671

Text #2

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1311899 (C4 (Web Text))

Max Activating Token Index: 949

Text #3

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1268. Min Act: -0.0001

Data Index: 932176 (C4 (Web Text))

Max Activating Token Index: 379

Text #4

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1381. Min Act: -0.0001

Data Index: 837466 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1335. Min Act: -0.0001

Data Index: 771764 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1495. Min Act: -0.0001

Data Index: 955444 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1358. Min Act: -0.0001

Data Index: 1339262 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1106364 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1299. Min Act: -0.0001

Data Index: 134278 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1398. Min Act: -0.0001

Data Index: 896705 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1435. Min Act: -0.0001

Data Index: 763636 (C4 (Web Text))

Max Activating Token Index: 256

Text #12

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1161906 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1385. Min Act: -0.0001

Data Index: 410738 (C4 (Web Text))

Max Activating Token Index: 547

Text #14

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1317. Min Act: -0.0001

Data Index: 596937 (C4 (Web Text))

Max Activating Token Index: 105

Text #15

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1338. Min Act: -0.0001

Data Index: 772722 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1278. Min Act: -0.0001

Data Index: 445797 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1144937 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1248. Min Act: -0.0001

Data Index: 570286 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.1605. Min Range: -0.1605

Max Act: 0.1278. Min Act: -0.0001

Data Index: 779352 (C4 (Web Text))

Max Activating Token Index: 557