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

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

Neuron 451 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: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1550385 (Python Code)

Max Activating Token Index: 532

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1497765 (Python Code)

Max Activating Token Index: 953

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1537580 (Python Code)

Max Activating Token Index: 50

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0320. Min Act: -0.0001

Data Index: 1536960 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1649977 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0312. Min Act: -0.0001

Data Index: 1501631 (Python Code)

Max Activating Token Index: 648

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0307. Min Act: -0.0001

Data Index: 1631402 (Python Code)

Max Activating Token Index: 591

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0310. Min Act: -0.0001

Data Index: 1625815 (Python Code)

Max Activating Token Index: 645

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1451184 (Python Code)

Max Activating Token Index: 624

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1572971 (Python Code)

Max Activating Token Index: 1007

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1487873 (Python Code)

Max Activating Token Index: 113

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0305. Min Act: -0.0001

Data Index: 1372234 (Python Code)

Max Activating Token Index: 617

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0304. Min Act: -0.0001

Data Index: 1424567 (Python Code)

Max Activating Token Index: 673

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0299. Min Act: -0.0001

Data Index: 1548677 (Python Code)

Max Activating Token Index: 271

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1549098 (Python Code)

Max Activating Token Index: 685

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0301. Min Act: -0.0001

Data Index: 1368906 (Python Code)

Max Activating Token Index: 448

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0298. Min Act: -0.0001

Data Index: 1375441 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0295. Min Act: -0.0001

Data Index: 1612799 (Python Code)

Max Activating Token Index: 824

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0291. Min Act: -0.0001

Data Index: 1366756 (Python Code)

Max Activating Token Index: 194

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0297. Min Act: -0.0001

Data Index: 1411638 (Python Code)

Max Activating Token Index: 825