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

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

Neuron 3083 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: 2.2652. Min Range: -2.2652

Max Act: 2.2652. Min Act: -0.0000

Data Index: 160879 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.9754. Min Act: -0.0000

Data Index: 489120 (C4 (Web Text))

Max Activating Token Index: 974

Text #2

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.7585. Min Act: -0.0000

Data Index: 977487 (C4 (Web Text))

Max Activating Token Index: 394

Text #3

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.7588. Min Act: -0.0000

Data Index: 897610 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.7968. Min Act: -0.0000

Data Index: 611339 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5175. Min Act: -0.0000

Data Index: 586963 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.6132. Min Act: -0.0000

Data Index: 1389081 (Python Code)

Max Activating Token Index: 233

Text #7

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1620720 (Python Code)

Max Activating Token Index: 496

Text #8

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.4749. Min Act: -0.0000

Data Index: 1410016 (Python Code)

Max Activating Token Index: 362

Text #9

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5583. Min Act: -0.0000

Data Index: 1404289 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5660. Min Act: -0.0000

Data Index: 1491749 (Python Code)

Max Activating Token Index: 376

Text #11

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5426. Min Act: -0.0000

Data Index: 1572063 (Python Code)

Max Activating Token Index: 532

Text #12

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.6478. Min Act: -0.0000

Data Index: 785530 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5393. Min Act: -0.0000

Data Index: 1483150 (Python Code)

Max Activating Token Index: 670

Text #14

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5487. Min Act: -0.0000

Data Index: 1453480 (Python Code)

Max Activating Token Index: 508

Text #15

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5157. Min Act: -0.0000

Data Index: 1524413 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1628932 (Python Code)

Max Activating Token Index: 241

Text #17

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.4981. Min Act: -0.0000

Data Index: 1574114 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.4900. Min Act: -0.0000

Data Index: 1517482 (Python Code)

Max Activating Token Index: 184

Text #19

Max Range: 2.2652. Min Range: -2.2652

Max Act: 1.4986. Min Act: -0.0000

Data Index: 1637935 (Python Code)

Max Activating Token Index: 507