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

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

Neuron 5235 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.5471. Min Act: -0.0000

Data Index: 1403123 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4944. Min Act: -0.0000

Data Index: 909038 (C4 (Web Text))

Max Activating Token Index: 368

Text #2

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1469988 (Python Code)

Max Activating Token Index: 717

Text #3

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1471299 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1454628 (Python Code)

Max Activating Token Index: 107

Text #5

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4048. Min Act: -0.0000

Data Index: 1456614 (Python Code)

Max Activating Token Index: 389

Text #6

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1544136 (Python Code)

Max Activating Token Index: 527

Text #7

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4517. Min Act: -0.0000

Data Index: 1379039 (Python Code)

Max Activating Token Index: 87

Text #8

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4343. Min Act: -0.0000

Data Index: 1410588 (Python Code)

Max Activating Token Index: 678

Text #9

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4262. Min Act: -0.0000

Data Index: 1650698 (Python Code)

Max Activating Token Index: 178

Text #10

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1403684 (Python Code)

Max Activating Token Index: 499

Text #11

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1485181 (Python Code)

Max Activating Token Index: 219

Text #12

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4025. Min Act: -0.0000

Data Index: 1414481 (Python Code)

Max Activating Token Index: 227

Text #13

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3938. Min Act: -0.0000

Data Index: 1381193 (Python Code)

Max Activating Token Index: 586

Text #14

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1320446 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3760. Min Act: -0.0000

Data Index: 968216 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3743. Min Act: -0.0000

Data Index: 1532134 (Python Code)

Max Activating Token Index: 525

Text #17

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3750. Min Act: -0.0000

Data Index: 582186 (C4 (Web Text))

Max Activating Token Index: 984

Text #18

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3578. Min Act: -0.0000

Data Index: 1482258 (Python Code)

Max Activating Token Index: 355

Text #19

Max Range: 0.5471. Min Range: -0.5471

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1617889 (Python Code)

Max Activating Token Index: 561