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

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

Neuron 2035 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2535. Min Range: -1.2535

Max Act: 1.2535. Min Act: -0.0000

Data Index: 1384580 (Python Code)

Max Activating Token Index: 119

Text #1

Max Range: 1.2535. Min Range: -1.2535

Max Act: 1.0988. Min Act: -0.0001

Data Index: 1462796 (Python Code)

Max Activating Token Index: 558

Text #2

Max Range: 1.2535. Min Range: -1.2535

Max Act: 1.0393. Min Act: -0.0000

Data Index: 1575317 (Python Code)

Max Activating Token Index: 419

Text #3

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1388333 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 1.2535. Min Range: -1.2535

Max Act: 1.0163. Min Act: -0.0000

Data Index: 1577217 (Python Code)

Max Activating Token Index: 686

Text #5

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1634522 (Python Code)

Max Activating Token Index: 349

Text #6

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.9034. Min Act: -0.0000

Data Index: 1595661 (Python Code)

Max Activating Token Index: 273

Text #7

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8563. Min Act: -0.0000

Data Index: 1393356 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8935. Min Act: -0.0000

Data Index: 1446785 (Python Code)

Max Activating Token Index: 551

Text #9

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8359. Min Act: -0.0000

Data Index: 1443130 (Python Code)

Max Activating Token Index: 689

Text #10

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.9054. Min Act: -0.0000

Data Index: 1551891 (Python Code)

Max Activating Token Index: 865

Text #11

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1550573 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8646. Min Act: -0.0000

Data Index: 1544300 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1432669 (Python Code)

Max Activating Token Index: 131

Text #14

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8081. Min Act: -0.0000

Data Index: 1364911 (Python Code)

Max Activating Token Index: 368

Text #15

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8297. Min Act: -0.0000

Data Index: 1450204 (Python Code)

Max Activating Token Index: 45

Text #16

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8315. Min Act: -0.0000

Data Index: 1360874 (Python Code)

Max Activating Token Index: 593

Text #17

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.8302. Min Act: -0.0000

Data Index: 1620126 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1538726 (Python Code)

Max Activating Token Index: 654

Text #19

Max Range: 1.2535. Min Range: -1.2535

Max Act: 0.7750. Min Act: -0.0000

Data Index: 1418887 (Python Code)

Max Activating Token Index: 197