Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3880 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.3076. Min Act: -0.0000

Data Index: 26122 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.1462. Min Act: -0.0000

Data Index: 1269375 (C4 (Web Text))

Max Activating Token Index: 544

Text #2

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.2223. Min Act: -0.0000

Data Index: 398092 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.0716. Min Act: -0.0000

Data Index: 1178357 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.1880. Min Act: -0.0000

Data Index: 996754 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.0798. Min Act: -0.0000

Data Index: 150363 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.9368. Min Act: -0.0000

Data Index: 536311 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.0387. Min Act: -0.0000

Data Index: 805583 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.0412. Min Act: -0.0000

Data Index: 697009 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.9131. Min Act: -0.0000

Data Index: 1173100 (C4 (Web Text))

Max Activating Token Index: 611

Text #10

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.8929. Min Act: -0.0000

Data Index: 901362 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 2.3076. Min Range: -2.3076

Max Act: 2.0835. Min Act: -0.0000

Data Index: 1093739 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.8604. Min Act: -0.0000

Data Index: 891505 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.9033. Min Act: -0.0000

Data Index: 450578 (C4 (Web Text))

Max Activating Token Index: 621

Text #14

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.8922. Min Act: -0.0000

Data Index: 879828 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.8739. Min Act: -0.0000

Data Index: 1056803 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.8321. Min Act: -0.0000

Data Index: 1245343 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.8295. Min Act: -0.0000

Data Index: 895920 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.7026. Min Act: -0.0000

Data Index: 1067841 (C4 (Web Text))

Max Activating Token Index: 599

Text #19

Max Range: 2.3076. Min Range: -2.3076

Max Act: 1.9013. Min Act: -0.0000

Data Index: 976423 (C4 (Web Text))

Max Activating Token Index: 1010