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

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

Neuron 5544 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1542. Min Range: -1.1542

Max Act: 1.1542. Min Act: -0.0000

Data Index: 1585668 (Python Code)

Max Activating Token Index: 935

Text #1

Max Range: 1.1542. Min Range: -1.1542

Max Act: 1.1508. Min Act: -0.0000

Data Index: 1655715 (Python Code)

Max Activating Token Index: 690

Text #2

Max Range: 1.1542. Min Range: -1.1542

Max Act: 1.0568. Min Act: -0.0000

Data Index: 1367577 (Python Code)

Max Activating Token Index: 404

Text #3

Max Range: 1.1542. Min Range: -1.1542

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1359943 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1559188 (Python Code)

Max Activating Token Index: 524

Text #5

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1399482 (Python Code)

Max Activating Token Index: 625

Text #6

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.9154. Min Act: -0.0000

Data Index: 1495595 (Python Code)

Max Activating Token Index: 698

Text #7

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1608398 (Python Code)

Max Activating Token Index: 49

Text #8

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8607. Min Act: -0.0000

Data Index: 1483945 (Python Code)

Max Activating Token Index: 169

Text #9

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8593. Min Act: -0.0000

Data Index: 1607551 (Python Code)

Max Activating Token Index: 42

Text #10

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1545219 (Python Code)

Max Activating Token Index: 210

Text #11

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8472. Min Act: -0.0000

Data Index: 1599254 (Python Code)

Max Activating Token Index: 494

Text #12

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1621918 (Python Code)

Max Activating Token Index: 132

Text #13

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.7907. Min Act: -0.0000

Data Index: 1552133 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8272. Min Act: -0.0000

Data Index: 1402741 (Python Code)

Max Activating Token Index: 233

Text #15

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1552845 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8487. Min Act: -0.0000

Data Index: 1636330 (Python Code)

Max Activating Token Index: 61

Text #17

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8279. Min Act: -0.0000

Data Index: 1436450 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8236. Min Act: -0.0000

Data Index: 1497304 (Python Code)

Max Activating Token Index: 566

Text #19

Max Range: 1.1542. Min Range: -1.1542

Max Act: 0.8172. Min Act: -0.0000

Data Index: 1481722 (Python Code)

Max Activating Token Index: 952