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

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

Neuron 5601 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: 4.5951. Min Range: -4.5951

Max Act: 4.5260. Min Act: -0.0000

Data Index: 1536572 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 4.5951. Min Range: -4.5951

Max Act: 4.3214. Min Act: -0.0000

Data Index: 1564480 (Python Code)

Max Activating Token Index: 609

Text #2

Max Range: 4.5951. Min Range: -4.5951

Max Act: 4.2834. Min Act: -0.0000

Data Index: 1440231 (Python Code)

Max Activating Token Index: 843

Text #3

Max Range: 4.5951. Min Range: -4.5951

Max Act: 4.3604. Min Act: -0.0000

Data Index: 1557325 (Python Code)

Max Activating Token Index: 297

Text #4

Max Range: 4.5951. Min Range: -4.5951

Max Act: 4.3040. Min Act: -0.0000

Data Index: 1529772 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.9200. Min Act: -0.0000

Data Index: 1629532 (Python Code)

Max Activating Token Index: 419

Text #6

Max Range: 4.5951. Min Range: -4.5951

Max Act: 4.4654. Min Act: -0.0000

Data Index: 1585423 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 4.5951. Min Range: -4.5951

Max Act: 4.5951. Min Act: -0.0000

Data Index: 1635571 (Python Code)

Max Activating Token Index: 191

Text #8

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.5692. Min Act: -0.0000

Data Index: 84244 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 4.5951. Min Range: -4.5951

Max Act: 4.1726. Min Act: -0.0000

Data Index: 1367569 (Python Code)

Max Activating Token Index: 541

Text #10

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.7599. Min Act: -0.0000

Data Index: 1463309 (Python Code)

Max Activating Token Index: 840

Text #11

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.8462. Min Act: -0.0000

Data Index: 600705 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.8571. Min Act: -0.0000

Data Index: 830382 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.8337. Min Act: -0.0000

Data Index: 1441153 (Python Code)

Max Activating Token Index: 1012

Text #14

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.6273. Min Act: -0.0000

Data Index: 1482918 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.7036. Min Act: -0.0000

Data Index: 1610675 (Python Code)

Max Activating Token Index: 527

Text #16

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.8759. Min Act: -0.0000

Data Index: 1513529 (Python Code)

Max Activating Token Index: 937

Text #17

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.6938. Min Act: -0.0000

Data Index: 425627 (C4 (Web Text))

Max Activating Token Index: 91

Text #18

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.5012. Min Act: -0.0000

Data Index: 373880 (C4 (Web Text))

Max Activating Token Index: 722

Text #19

Max Range: 4.5951. Min Range: -4.5951

Max Act: 3.5166. Min Act: -0.0000

Data Index: 1584385 (Python Code)

Max Activating Token Index: 203