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

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

Neuron 485 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.2845. Min Act: -0.0000

Data Index: 1634892 (Python Code)

Max Activating Token Index: 908

Text #1

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.1173. Min Act: -0.0000

Data Index: 1644779 (Python Code)

Max Activating Token Index: 460

Text #2

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1448365 (Python Code)

Max Activating Token Index: 88

Text #3

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1437592 (Python Code)

Max Activating Token Index: 329

Text #4

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1421920 (Python Code)

Max Activating Token Index: 381

Text #5

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.1081. Min Act: -0.0000

Data Index: 1613514 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.1025. Min Act: 0.0000

Data Index: 1630900 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0569. Min Act: -0.0000

Data Index: 1451179 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1455538 (Python Code)

Max Activating Token Index: 1015

Text #9

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9876. Min Act: -0.0000

Data Index: 1557368 (Python Code)

Max Activating Token Index: 552

Text #10

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0153. Min Act: -0.0000

Data Index: 1546134 (Python Code)

Max Activating Token Index: 726

Text #11

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0737. Min Act: -0.0000

Data Index: 1438558 (Python Code)

Max Activating Token Index: 61

Text #12

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1612650 (Python Code)

Max Activating Token Index: 111

Text #13

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1494672 (Python Code)

Max Activating Token Index: 629

Text #14

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1360094 (Python Code)

Max Activating Token Index: 166

Text #15

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1461110 (Python Code)

Max Activating Token Index: 677

Text #16

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9438. Min Act: -0.0000

Data Index: 1469825 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 1.2845. Min Range: -1.2845

Max Act: 1.0254. Min Act: -0.0000

Data Index: 1400670 (Python Code)

Max Activating Token Index: 162

Text #18

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9573. Min Act: -0.0000

Data Index: 1616990 (Python Code)

Max Activating Token Index: 298

Text #19

Max Range: 1.2845. Min Range: -1.2845

Max Act: 0.9244. Min Act: -0.0000

Data Index: 1648398 (Python Code)

Max Activating Token Index: 1003