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

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

Neuron 5431 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: 1.8688. Min Range: -1.8688

Max Act: 1.8688. Min Act: -0.0000

Data Index: 1481201 (Python Code)

Max Activating Token Index: 199

Text #1

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7886. Min Act: -0.0000

Data Index: 1490466 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.6552. Min Act: -0.0000

Data Index: 1366011 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.7006. Min Act: -0.0000

Data Index: 1477247 (Python Code)

Max Activating Token Index: 968

Text #4

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.6569. Min Act: -0.0000

Data Index: 1530022 (Python Code)

Max Activating Token Index: 625

Text #5

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5069. Min Act: -0.0000

Data Index: 1483374 (Python Code)

Max Activating Token Index: 456

Text #6

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5564. Min Act: -0.0000

Data Index: 1387380 (Python Code)

Max Activating Token Index: 541

Text #7

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1552785 (Python Code)

Max Activating Token Index: 312

Text #8

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1601800 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5693. Min Act: -0.0000

Data Index: 1389365 (Python Code)

Max Activating Token Index: 415

Text #10

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5093. Min Act: -0.0000

Data Index: 1380292 (Python Code)

Max Activating Token Index: 540

Text #11

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1393813 (Python Code)

Max Activating Token Index: 890

Text #12

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.4913. Min Act: -0.0000

Data Index: 1415825 (Python Code)

Max Activating Token Index: 285

Text #13

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1642971 (Python Code)

Max Activating Token Index: 498

Text #14

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.6108. Min Act: -0.0000

Data Index: 1400656 (Python Code)

Max Activating Token Index: 242

Text #15

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1155911 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1587351 (Python Code)

Max Activating Token Index: 523

Text #17

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1519051 (Python Code)

Max Activating Token Index: 515

Text #18

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.3500. Min Act: -0.0000

Data Index: 1448520 (Python Code)

Max Activating Token Index: 940

Text #19

Max Range: 1.8688. Min Range: -1.8688

Max Act: 1.4322. Min Act: -0.0000

Data Index: 1461423 (Python Code)

Max Activating Token Index: 216