Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2685 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.3006. Min Act: -0.0000

Data Index: 1602048 (Python Code)

Max Activating Token Index: 903

Text #1

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1576596 (Python Code)

Max Activating Token Index: 555

Text #2

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1613001 (Python Code)

Max Activating Token Index: 970

Text #3

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.2069. Min Act: -0.0000

Data Index: 1432534 (Python Code)

Max Activating Token Index: 939

Text #4

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.0566. Min Act: -0.0000

Data Index: 1397359 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.0631. Min Act: -0.0000

Data Index: 1457382 (Python Code)

Max Activating Token Index: 501

Text #6

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.0610. Min Act: -0.0000

Data Index: 1440326 (Python Code)

Max Activating Token Index: 431

Text #7

Max Range: 1.3006. Min Range: -1.3006

Max Act: 1.0380. Min Act: -0.0000

Data Index: 1550875 (Python Code)

Max Activating Token Index: 562

Text #8

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.9591. Min Act: -0.0000

Data Index: 1540479 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1531952 (Python Code)

Max Activating Token Index: 374

Text #10

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.8515. Min Act: 0.0000

Data Index: 1557695 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.8273. Min Act: -0.0000

Data Index: 1452434 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.8561. Min Act: -0.0000

Data Index: 1378472 (Python Code)

Max Activating Token Index: 302

Text #13

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.8854. Min Act: -0.0000

Data Index: 1528467 (Python Code)

Max Activating Token Index: 881

Text #14

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.8206. Min Act: -0.0000

Data Index: 1514380 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.7484. Min Act: -0.0000

Data Index: 1553685 (Python Code)

Max Activating Token Index: 841

Text #16

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.7316. Min Act: -0.0000

Data Index: 1391245 (Python Code)

Max Activating Token Index: 423

Text #17

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.7181. Min Act: -0.0000

Data Index: 1601054 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.6817. Min Act: -0.0000

Data Index: 1559784 (Python Code)

Max Activating Token Index: 581

Text #19

Max Range: 1.3006. Min Range: -1.3006

Max Act: 0.7319. Min Act: -0.0000

Data Index: 1579384 (Python Code)

Max Activating Token Index: 776