Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1816 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.3725. Min Act: -0.0001

Data Index: 1532066 (Python Code)

Max Activating Token Index: 163

Text #1

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.2341. Min Act: -0.0001

Data Index: 1551055 (Python Code)

Max Activating Token Index: 404

Text #2

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.1986. Min Act: -0.0001

Data Index: 1514834 (Python Code)

Max Activating Token Index: 566

Text #3

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.1732. Min Act: -0.0001

Data Index: 1649396 (Python Code)

Max Activating Token Index: 721

Text #4

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0924. Min Act: -0.0001

Data Index: 1627598 (Python Code)

Max Activating Token Index: 131

Text #5

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0596. Min Act: -0.0001

Data Index: 1398245 (Python Code)

Max Activating Token Index: 132

Text #6

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0081. Min Act: -0.0001

Data Index: 1594855 (Python Code)

Max Activating Token Index: 775

Text #7

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0369. Min Act: -0.0001

Data Index: 1530041 (Python Code)

Max Activating Token Index: 463

Text #8

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.1157. Min Act: -0.0001

Data Index: 1542370 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0604. Min Act: -0.0001

Data Index: 1372105 (Python Code)

Max Activating Token Index: 38

Text #10

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9924. Min Act: -0.0001

Data Index: 1469011 (Python Code)

Max Activating Token Index: 154

Text #11

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9778. Min Act: -0.0001

Data Index: 1644038 (Python Code)

Max Activating Token Index: 901

Text #12

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0062. Min Act: -0.0001

Data Index: 1444112 (Python Code)

Max Activating Token Index: 628

Text #13

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9689. Min Act: -0.0001

Data Index: 1481274 (Python Code)

Max Activating Token Index: 20

Text #14

Max Range: 1.3725. Min Range: -1.3725

Max Act: 1.0285. Min Act: -0.0001

Data Index: 1540240 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9645. Min Act: -0.0001

Data Index: 1548235 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9909. Min Act: -0.0001

Data Index: 1406087 (Python Code)

Max Activating Token Index: 6

Text #17

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9815. Min Act: -0.0001

Data Index: 1560477 (Python Code)

Max Activating Token Index: 369

Text #18

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9995. Min Act: -0.0001

Data Index: 1573564 (Python Code)

Max Activating Token Index: 105

Text #19

Max Range: 1.3725. Min Range: -1.3725

Max Act: 0.9078. Min Act: -0.0001

Data Index: 1455670 (Python Code)

Max Activating Token Index: 973