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

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

Neuron 5670 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3006. Min Range: -5.3006

Max Act: 5.3006. Min Act: -0.0000

Data Index: 1464517 (Python Code)

Max Activating Token Index: 391

Text #1

Max Range: 5.3006. Min Range: -5.3006

Max Act: 5.2358. Min Act: -0.0000

Data Index: 1437552 (Python Code)

Max Activating Token Index: 149

Text #2

Max Range: 5.3006. Min Range: -5.3006

Max Act: 5.1941. Min Act: -0.0000

Data Index: 1527662 (Python Code)

Max Activating Token Index: 973

Text #3

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.8158. Min Act: -0.0000

Data Index: 1412538 (Python Code)

Max Activating Token Index: 234

Text #4

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.6238. Min Act: -0.0000

Data Index: 1443944 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.6142. Min Act: -0.0000

Data Index: 1402607 (Python Code)

Max Activating Token Index: 466

Text #6

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.4069. Min Act: -0.0000

Data Index: 1543217 (Python Code)

Max Activating Token Index: 833

Text #7

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.5030. Min Act: -0.0000

Data Index: 1430722 (Python Code)

Max Activating Token Index: 603

Text #8

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.4403. Min Act: -0.0000

Data Index: 1522126 (Python Code)

Max Activating Token Index: 977

Text #9

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.6327. Min Act: -0.0000

Data Index: 1625616 (Python Code)

Max Activating Token Index: 968

Text #10

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.3791. Min Act: -0.0000

Data Index: 1477168 (Python Code)

Max Activating Token Index: 825

Text #11

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.0710. Min Act: -0.0000

Data Index: 1473677 (Python Code)

Max Activating Token Index: 906

Text #12

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.1689. Min Act: -0.0000

Data Index: 1422149 (Python Code)

Max Activating Token Index: 779

Text #13

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.1200. Min Act: -0.0000

Data Index: 1566512 (Python Code)

Max Activating Token Index: 90

Text #14

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.0598. Min Act: -0.0000

Data Index: 1543836 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 5.3006. Min Range: -5.3006

Max Act: 4.0475. Min Act: -0.0000

Data Index: 1498139 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 5.3006. Min Range: -5.3006

Max Act: 3.9134. Min Act: -0.0000

Data Index: 1436121 (Python Code)

Max Activating Token Index: 201

Text #17

Max Range: 5.3006. Min Range: -5.3006

Max Act: 3.7113. Min Act: -0.0000

Data Index: 1613507 (Python Code)

Max Activating Token Index: 267

Text #18

Max Range: 5.3006. Min Range: -5.3006

Max Act: 3.8203. Min Act: -0.0000

Data Index: 1368117 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 5.3006. Min Range: -5.3006

Max Act: 3.9788. Min Act: -0.0000

Data Index: 1478974 (Python Code)

Max Activating Token Index: 919