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

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

Neuron 1543 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1284102 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6107. Min Act: -0.0000

Data Index: 757133 (C4 (Web Text))

Max Activating Token Index: 826

Text #2

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1277811 (C4 (Web Text))

Max Activating Token Index: 665

Text #3

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6033. Min Act: -0.0000

Data Index: 843776 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6522. Min Act: -0.0001

Data Index: 653276 (C4 (Web Text))

Max Activating Token Index: 344

Text #5

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6041. Min Act: -0.0001

Data Index: 1242033 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6018. Min Act: -0.0001

Data Index: 779375 (C4 (Web Text))

Max Activating Token Index: 892

Text #7

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6072. Min Act: -0.0000

Data Index: 550474 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5598. Min Act: -0.0001

Data Index: 477188 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.6081. Min Act: -0.0001

Data Index: 401463 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5633. Min Act: -0.0001

Data Index: 1010533 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5892. Min Act: -0.0000

Data Index: 1184 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5608. Min Act: -0.0001

Data Index: 1323513 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1279677 (C4 (Web Text))

Max Activating Token Index: 562

Text #14

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5369. Min Act: -0.0001

Data Index: 688815 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5284. Min Act: -0.0000

Data Index: 685380 (C4 (Web Text))

Max Activating Token Index: 856

Text #16

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5633. Min Act: -0.0001

Data Index: 987951 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.5705. Min Act: -0.0001

Data Index: 294195 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4946. Min Act: -0.0001

Data Index: 270072 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.6522. Min Range: -0.6522

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1184006 (C4 (Web Text))

Max Activating Token Index: 325