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

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

Neuron 3790 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.7590. Min Act: -0.0001

Data Index: 1416710 (Python Code)

Max Activating Token Index: 400

Text #1

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1548119 (Python Code)

Max Activating Token Index: 107

Text #2

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.7233. Min Act: -0.0001

Data Index: 1545209 (Python Code)

Max Activating Token Index: 70

Text #3

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.7123. Min Act: -0.0001

Data Index: 1573501 (Python Code)

Max Activating Token Index: 675

Text #4

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6621. Min Act: -0.0001

Data Index: 1376907 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6676. Min Act: -0.0001

Data Index: 1655098 (Python Code)

Max Activating Token Index: 654

Text #6

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.7271. Min Act: -0.0001

Data Index: 1645437 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6296. Min Act: -0.0001

Data Index: 1520474 (Python Code)

Max Activating Token Index: 251

Text #8

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1566644 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6553. Min Act: -0.0001

Data Index: 1505668 (Python Code)

Max Activating Token Index: 264

Text #10

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1485023 (Python Code)

Max Activating Token Index: 120

Text #11

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1527803 (Python Code)

Max Activating Token Index: 34

Text #12

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6297. Min Act: -0.0001

Data Index: 1586996 (Python Code)

Max Activating Token Index: 14

Text #13

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6662. Min Act: -0.0000

Data Index: 1441301 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6251. Min Act: -0.0001

Data Index: 1444488 (Python Code)

Max Activating Token Index: 54

Text #15

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6417. Min Act: -0.0000

Data Index: 1457819 (Python Code)

Max Activating Token Index: 243

Text #16

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6239. Min Act: -0.0001

Data Index: 1367899 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1557936 (Python Code)

Max Activating Token Index: 19

Text #18

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.6560. Min Act: -0.0000

Data Index: 1574039 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.7590. Min Range: -0.7590

Max Act: 0.5976. Min Act: -0.0001

Data Index: 1516107 (Python Code)

Max Activating Token Index: 630