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

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

Neuron 2868 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9498. Min Act: -0.0001

Data Index: 1444965 (Python Code)

Max Activating Token Index: 106

Text #1

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9174. Min Act: -0.0001

Data Index: 1447920 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9034. Min Act: -0.0001

Data Index: 1586307 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9308. Min Act: -0.0001

Data Index: 1591350 (Python Code)

Max Activating Token Index: 729

Text #4

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9268. Min Act: -0.0001

Data Index: 1487515 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.8718. Min Act: -0.0001

Data Index: 1458346 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9165. Min Act: -0.0001

Data Index: 1595218 (Python Code)

Max Activating Token Index: 466

Text #7

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.9236. Min Act: -0.0001

Data Index: 1386274 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7702. Min Act: -0.0001

Data Index: 1447411 (Python Code)

Max Activating Token Index: 575

Text #9

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.8434. Min Act: -0.0001

Data Index: 1401136 (Python Code)

Max Activating Token Index: 108

Text #10

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7433. Min Act: -0.0001

Data Index: 1374610 (Python Code)

Max Activating Token Index: 68

Text #11

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.8118. Min Act: -0.0001

Data Index: 1428492 (Python Code)

Max Activating Token Index: 536

Text #12

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7877. Min Act: -0.0001

Data Index: 1474292 (Python Code)

Max Activating Token Index: 105

Text #13

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7303. Min Act: -0.0001

Data Index: 1489544 (Python Code)

Max Activating Token Index: 178

Text #14

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.8436. Min Act: -0.0001

Data Index: 1553061 (Python Code)

Max Activating Token Index: 138

Text #15

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7752. Min Act: -0.0001

Data Index: 1639517 (Python Code)

Max Activating Token Index: 518

Text #16

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7248. Min Act: -0.0001

Data Index: 1457159 (Python Code)

Max Activating Token Index: 139

Text #17

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7678. Min Act: -0.0001

Data Index: 1480747 (Python Code)

Max Activating Token Index: 343

Text #18

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7137. Min Act: -0.0001

Data Index: 1620671 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 0.9498. Min Range: -0.9498

Max Act: 0.7759. Min Act: -0.0001

Data Index: 1416678 (Python Code)

Max Activating Token Index: 467