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

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

Neuron 823 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1640528 (Python Code)

Max Activating Token Index: 392

Text #1

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1388877 (Python Code)

Max Activating Token Index: 585

Text #2

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.5329. Min Act: -0.0000

Data Index: 1546274 (Python Code)

Max Activating Token Index: 414

Text #3

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1632374 (Python Code)

Max Activating Token Index: 890

Text #4

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.5135. Min Act: -0.0000

Data Index: 1492490 (Python Code)

Max Activating Token Index: 578

Text #5

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1149734 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.5187. Min Act: -0.0000

Data Index: 1642050 (Python Code)

Max Activating Token Index: 276

Text #7

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4657. Min Act: -0.0000

Data Index: 1564867 (Python Code)

Max Activating Token Index: 467

Text #8

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1582348 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1571295 (Python Code)

Max Activating Token Index: 218

Text #10

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4287. Min Act: -0.0000

Data Index: 1546343 (Python Code)

Max Activating Token Index: 617

Text #11

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1384008 (Python Code)

Max Activating Token Index: 887

Text #12

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4125. Min Act: -0.0000

Data Index: 1499948 (Python Code)

Max Activating Token Index: 382

Text #13

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4227. Min Act: -0.0000

Data Index: 1432678 (Python Code)

Max Activating Token Index: 371

Text #14

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3636. Min Act: -0.0000

Data Index: 640751 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.4064. Min Act: -0.0000

Data Index: 181574 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3990. Min Act: -0.0000

Data Index: 1381363 (Python Code)

Max Activating Token Index: 911

Text #17

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3611. Min Act: -0.0000

Data Index: 1042778 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3801. Min Act: -0.0000

Data Index: 1458036 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 0.5656. Min Range: -0.5656

Max Act: 0.3571. Min Act: -0.0000

Data Index: 1526089 (Python Code)

Max Activating Token Index: 456