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

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

Neuron 1602 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: 0.0419. Min Range: -0.0419

Max Act: 0.0419. Min Act: -0.0002

Data Index: 166923 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0365. Min Act: -0.0001

Data Index: 23238 (C4 (Web Text))

Max Activating Token Index: 964

Text #2

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0286. Min Act: -0.0001

Data Index: 1510738 (Python Code)

Max Activating Token Index: 730

Text #3

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0291. Min Act: -0.0001

Data Index: 358793 (C4 (Web Text))

Max Activating Token Index: 430

Text #4

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1494782 (Python Code)

Max Activating Token Index: 744

Text #5

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1358570 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0287. Min Act: -0.0001

Data Index: 1443294 (Python Code)

Max Activating Token Index: 568

Text #7

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1626540 (Python Code)

Max Activating Token Index: 27

Text #8

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0302. Min Act: -0.0001

Data Index: 1442528 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0288. Min Act: -0.0001

Data Index: 344224 (C4 (Web Text))

Max Activating Token Index: 473

Text #10

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1244964 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0293. Min Act: -0.0001

Data Index: 1377807 (Python Code)

Max Activating Token Index: 666

Text #12

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1469127 (Python Code)

Max Activating Token Index: 24

Text #13

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0288. Min Act: -0.0001

Data Index: 1395624 (Python Code)

Max Activating Token Index: 393

Text #14

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0289. Min Act: -0.0001

Data Index: 1506453 (Python Code)

Max Activating Token Index: 592

Text #15

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0282. Min Act: -0.0001

Data Index: 1472195 (Python Code)

Max Activating Token Index: 508

Text #16

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1196747 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0281. Min Act: -0.0001

Data Index: 1509569 (Python Code)

Max Activating Token Index: 921

Text #18

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0280. Min Act: -0.0001

Data Index: 1609933 (Python Code)

Max Activating Token Index: 587

Text #19

Max Range: 0.0419. Min Range: -0.0419

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1595130 (Python Code)

Max Activating Token Index: 9