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

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

Neuron 4127 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: 1.0441. Min Range: -1.0441

Max Act: 1.0441. Min Act: -0.0001

Data Index: 1653983 (Python Code)

Max Activating Token Index: 246

Text #1

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0289. Min Act: -0.0001

Data Index: 1371107 (Python Code)

Max Activating Token Index: 980

Text #2

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9452. Min Act: -0.0000

Data Index: 1412409 (Python Code)

Max Activating Token Index: 93

Text #3

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9462. Min Act: -0.0001

Data Index: 1395112 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9984. Min Act: -0.0001

Data Index: 1445009 (Python Code)

Max Activating Token Index: 206

Text #5

Max Range: 1.0441. Min Range: -1.0441

Max Act: 1.0136. Min Act: -0.0000

Data Index: 1395445 (Python Code)

Max Activating Token Index: 283

Text #6

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9462. Min Act: -0.0001

Data Index: 1557270 (Python Code)

Max Activating Token Index: 133

Text #7

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9393. Min Act: -0.0001

Data Index: 1628706 (Python Code)

Max Activating Token Index: 379

Text #8

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8988. Min Act: -0.0001

Data Index: 1563073 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1456069 (Python Code)

Max Activating Token Index: 650

Text #10

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8493. Min Act: -0.0001

Data Index: 1517498 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7895. Min Act: -0.0001

Data Index: 1562836 (Python Code)

Max Activating Token Index: 312

Text #12

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8100. Min Act: -0.0001

Data Index: 809192 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8206. Min Act: -0.0001

Data Index: 1429265 (Python Code)

Max Activating Token Index: 342

Text #14

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8375. Min Act: -0.0001

Data Index: 1404178 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.9345. Min Act: -0.0000

Data Index: 1538275 (Python Code)

Max Activating Token Index: 298

Text #16

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7648. Min Act: -0.0001

Data Index: 1509352 (Python Code)

Max Activating Token Index: 412

Text #17

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.7944. Min Act: -0.0001

Data Index: 1474188 (Python Code)

Max Activating Token Index: 932

Text #18

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8515. Min Act: -0.0001

Data Index: 1391828 (Python Code)

Max Activating Token Index: 255

Text #19

Max Range: 1.0441. Min Range: -1.0441

Max Act: 0.8498. Min Act: -0.0001

Data Index: 1429288 (Python Code)

Max Activating Token Index: 979