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

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

Neuron 2181 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: 0.7230. Min Range: -0.7230

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1644917 (Python Code)

Max Activating Token Index: 236

Text #1

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1394166 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5913. Min Act: -0.0000

Data Index: 1418687 (Python Code)

Max Activating Token Index: 309

Text #3

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1606165 (Python Code)

Max Activating Token Index: 945

Text #4

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5677. Min Act: -0.0000

Data Index: 1600725 (Python Code)

Max Activating Token Index: 119

Text #5

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1603731 (Python Code)

Max Activating Token Index: 90

Text #6

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.5033. Min Act: -0.0000

Data Index: 1370877 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1415625 (Python Code)

Max Activating Token Index: 998

Text #8

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1489112 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1408736 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1484124 (Python Code)

Max Activating Token Index: 150

Text #11

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4906. Min Act: -0.0000

Data Index: 1462929 (Python Code)

Max Activating Token Index: 744

Text #12

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4896. Min Act: -0.0000

Data Index: 1551175 (Python Code)

Max Activating Token Index: 630

Text #13

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4841. Min Act: -0.0000

Data Index: 1373020 (Python Code)

Max Activating Token Index: 572

Text #14

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4684. Min Act: -0.0000

Data Index: 1515555 (Python Code)

Max Activating Token Index: 108

Text #15

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1429910 (Python Code)

Max Activating Token Index: 707

Text #16

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1459384 (Python Code)

Max Activating Token Index: 267

Text #17

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4647. Min Act: -0.0000

Data Index: 1432597 (Python Code)

Max Activating Token Index: 385

Text #18

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4521. Min Act: -0.0000

Data Index: 1456627 (Python Code)

Max Activating Token Index: 204

Text #19

Max Range: 0.7230. Min Range: -0.7230

Max Act: 0.4485. Min Act: -0.0000

Data Index: 1494146 (Python Code)

Max Activating Token Index: 507