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

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

Neuron 2753 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: 3.5114. Min Range: -3.5114

Max Act: 3.3026. Min Act: -0.0000

Data Index: 1522353 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.5114. Min Act: -0.0000

Data Index: 1435381 (Python Code)

Max Activating Token Index: 683

Text #2

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.4995. Min Act: -0.0000

Data Index: 1452237 (Python Code)

Max Activating Token Index: 514

Text #3

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.2067. Min Act: -0.0000

Data Index: 1618307 (Python Code)

Max Activating Token Index: 417

Text #4

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.1105. Min Act: -0.0000

Data Index: 1584449 (Python Code)

Max Activating Token Index: 922

Text #5

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.1400. Min Act: -0.0000

Data Index: 1503354 (Python Code)

Max Activating Token Index: 43

Text #6

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.2609. Min Act: -0.0000

Data Index: 1472601 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.0973. Min Act: -0.0000

Data Index: 1527970 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.7785. Min Act: -0.0000

Data Index: 1540263 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.9224. Min Act: -0.0000

Data Index: 1643703 (Python Code)

Max Activating Token Index: 735

Text #10

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.0579. Min Act: -0.0000

Data Index: 1464632 (Python Code)

Max Activating Token Index: 71

Text #11

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.0677. Min Act: -0.0000

Data Index: 1431788 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.0434. Min Act: -0.0000

Data Index: 1403655 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.8547. Min Act: -0.0000

Data Index: 1615126 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.8487. Min Act: -0.0000

Data Index: 1448250 (Python Code)

Max Activating Token Index: 604

Text #15

Max Range: 3.5114. Min Range: -3.5114

Max Act: 3.2784. Min Act: -0.0000

Data Index: 71007 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.8169. Min Act: -0.0000

Data Index: 1425869 (Python Code)

Max Activating Token Index: 934

Text #17

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.8006. Min Act: -0.0000

Data Index: 1477026 (Python Code)

Max Activating Token Index: 934

Text #18

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.9463. Min Act: -0.0000

Data Index: 1507914 (Python Code)

Max Activating Token Index: 590

Text #19

Max Range: 3.5114. Min Range: -3.5114

Max Act: 2.6773. Min Act: -0.0000

Data Index: 1502124 (Python Code)

Max Activating Token Index: 1004