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

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

Neuron 3741 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0002

Data Index: 692043 (C4 (Web Text))

Max Activating Token Index: 457

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0387. Min Act: -0.0002

Data Index: 896420 (C4 (Web Text))

Max Activating Token Index: 489

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0390. Min Act: -0.0002

Data Index: 580134 (C4 (Web Text))

Max Activating Token Index: 80

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0357. Min Act: -0.0002

Data Index: 1420494 (Python Code)

Max Activating Token Index: 508

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0343. Min Act: -0.0002

Data Index: 1076974 (C4 (Web Text))

Max Activating Token Index: 848

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0326. Min Act: -0.0002

Data Index: 510238 (C4 (Web Text))

Max Activating Token Index: 400

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1469784 (Python Code)

Max Activating Token Index: 726

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1460126 (Python Code)

Max Activating Token Index: 1018

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0313. Min Act: -0.0002

Data Index: 903520 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0324. Min Act: -0.0002

Data Index: 1409209 (Python Code)

Max Activating Token Index: 515

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0288. Min Act: -0.0002

Data Index: 132801 (C4 (Web Text))

Max Activating Token Index: 311

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0282. Min Act: -0.0002

Data Index: 365010 (C4 (Web Text))

Max Activating Token Index: 50

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0259. Min Act: -0.0002

Data Index: 638926 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1399133 (Python Code)

Max Activating Token Index: 192

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0277. Min Act: -0.0002

Data Index: 677394 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1394656 (Python Code)

Max Activating Token Index: 705

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1056774 (C4 (Web Text))

Max Activating Token Index: 347

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1373113 (Python Code)

Max Activating Token Index: 215

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1630186 (Python Code)

Max Activating Token Index: 170

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0267. Min Act: -0.0002

Data Index: 379782 (C4 (Web Text))

Max Activating Token Index: 196