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

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

Neuron 2730 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.6455. Min Act: -0.0000

Data Index: 1487661 (Python Code)

Max Activating Token Index: 578

Text #1

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1559628 (Python Code)

Max Activating Token Index: 905

Text #2

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1593369 (Python Code)

Max Activating Token Index: 870

Text #3

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5637. Min Act: -0.0000

Data Index: 1490147 (Python Code)

Max Activating Token Index: 961

Text #4

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5245. Min Act: -0.0000

Data Index: 1450922 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1362448 (Python Code)

Max Activating Token Index: 224

Text #6

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1450968 (Python Code)

Max Activating Token Index: 1013

Text #7

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1647217 (Python Code)

Max Activating Token Index: 684

Text #8

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1575338 (Python Code)

Max Activating Token Index: 898

Text #9

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1552156 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1453244 (Python Code)

Max Activating Token Index: 357

Text #11

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1397674 (Python Code)

Max Activating Token Index: 928

Text #12

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1627611 (Python Code)

Max Activating Token Index: 566

Text #13

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.5065. Min Act: -0.0000

Data Index: 1414707 (Python Code)

Max Activating Token Index: 786

Text #14

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1518236 (Python Code)

Max Activating Token Index: 752

Text #15

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1648620 (Python Code)

Max Activating Token Index: 709

Text #16

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4568. Min Act: -0.0000

Data Index: 1475245 (Python Code)

Max Activating Token Index: 914

Text #17

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1461488 (Python Code)

Max Activating Token Index: 306

Text #18

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4494. Min Act: -0.0000

Data Index: 1473806 (Python Code)

Max Activating Token Index: 258

Text #19

Max Range: 0.6455. Min Range: -0.6455

Max Act: 0.4457. Min Act: -0.0000

Data Index: 1550896 (Python Code)

Max Activating Token Index: 813