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

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

Neuron 3763 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0362. Min Act: -0.0002

Data Index: 1616669 (Python Code)

Max Activating Token Index: 130

Text #1

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0356. Min Act: -0.0001

Data Index: 1360252 (Python Code)

Max Activating Token Index: 577

Text #2

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0344. Min Act: -0.0001

Data Index: 1488165 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0339. Min Act: -0.0001

Data Index: 1480724 (Python Code)

Max Activating Token Index: 45

Text #4

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0326. Min Act: -0.0001

Data Index: 1525824 (Python Code)

Max Activating Token Index: 720

Text #5

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1544836 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1364003 (Python Code)

Max Activating Token Index: 18

Text #7

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1602270 (Python Code)

Max Activating Token Index: 170

Text #8

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1650944 (Python Code)

Max Activating Token Index: 70

Text #9

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0296. Min Act: -0.0001

Data Index: 1401182 (Python Code)

Max Activating Token Index: 351

Text #10

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1557712 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0290. Min Act: -0.0001

Data Index: 1566709 (Python Code)

Max Activating Token Index: 233

Text #12

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0283. Min Act: -0.0001

Data Index: 1515179 (Python Code)

Max Activating Token Index: 380

Text #13

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0287. Min Act: -0.0002

Data Index: 1414490 (Python Code)

Max Activating Token Index: 27

Text #14

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1416688 (Python Code)

Max Activating Token Index: 195

Text #15

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1423324 (Python Code)

Max Activating Token Index: 666

Text #16

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0282. Min Act: -0.0001

Data Index: 559607 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0278. Min Act: -0.0001

Data Index: 1598815 (Python Code)

Max Activating Token Index: 444

Text #18

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0285. Min Act: -0.0001

Data Index: 1408643 (Python Code)

Max Activating Token Index: 549

Text #19

Max Range: 0.0362. Min Range: -0.0362

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1607268 (Python Code)

Max Activating Token Index: 52