Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2415 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.5822. Min Act: -0.0001

Data Index: 1526735 (Python Code)

Max Activating Token Index: 434

Text #1

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.4350. Min Act: -0.0001

Data Index: 1499632 (Python Code)

Max Activating Token Index: 532

Text #2

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.2973. Min Act: -0.0001

Data Index: 1489304 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.3651. Min Act: -0.0001

Data Index: 1419761 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.2436. Min Act: -0.0001

Data Index: 1642543 (Python Code)

Max Activating Token Index: 553

Text #5

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.0809. Min Act: -0.0001

Data Index: 1451046 (Python Code)

Max Activating Token Index: 1000

Text #6

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.1721. Min Act: -0.0000

Data Index: 1607448 (Python Code)

Max Activating Token Index: 501

Text #7

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.2103. Min Act: -0.0000

Data Index: 1389364 (Python Code)

Max Activating Token Index: 534

Text #8

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.0335. Min Act: -0.0000

Data Index: 1374462 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.0611. Min Act: -0.0001

Data Index: 1555185 (Python Code)

Max Activating Token Index: 380

Text #10

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.0243. Min Act: -0.0001

Data Index: 1504054 (Python Code)

Max Activating Token Index: 52

Text #11

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.0851. Min Act: -0.0001

Data Index: 1634744 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.1103. Min Act: -0.0001

Data Index: 1611224 (Python Code)

Max Activating Token Index: 731

Text #13

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.0990. Min Act: -0.0001

Data Index: 1546519 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 1.5822. Min Range: -1.5822

Max Act: 0.9095. Min Act: -0.0001

Data Index: 1447504 (Python Code)

Max Activating Token Index: 67

Text #15

Max Range: 1.5822. Min Range: -1.5822

Max Act: 0.9285. Min Act: -0.0001

Data Index: 1559370 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 1.5822. Min Range: -1.5822

Max Act: 0.9223. Min Act: -0.0001

Data Index: 1593209 (Python Code)

Max Activating Token Index: 592

Text #17

Max Range: 1.5822. Min Range: -1.5822

Max Act: 0.8801. Min Act: -0.0001

Data Index: 1466485 (Python Code)

Max Activating Token Index: 688

Text #18

Max Range: 1.5822. Min Range: -1.5822

Max Act: 1.0208. Min Act: -0.0001

Data Index: 1512634 (Python Code)

Max Activating Token Index: 674

Text #19

Max Range: 1.5822. Min Range: -1.5822

Max Act: 0.9494. Min Act: -0.0001

Data Index: 1398879 (Python Code)

Max Activating Token Index: 892