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

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

Neuron 3175 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9503. Min Act: -0.0001

Data Index: 1203403 (C4 (Web Text))

Max Activating Token Index: 712

Text #1

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.9540. Min Act: -0.0001

Data Index: 988927 (C4 (Web Text))

Max Activating Token Index: 684

Text #2

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8768. Min Act: -0.0001

Data Index: 993123 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8529. Min Act: -0.0001

Data Index: 396033 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8140. Min Act: -0.0001

Data Index: 1160891 (C4 (Web Text))

Max Activating Token Index: 407

Text #5

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7680. Min Act: -0.0001

Data Index: 1143748 (C4 (Web Text))

Max Activating Token Index: 691

Text #6

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7836. Min Act: -0.0001

Data Index: 1249801 (C4 (Web Text))

Max Activating Token Index: 372

Text #7

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7213. Min Act: -0.0001

Data Index: 571670 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7807. Min Act: -0.0001

Data Index: 635893 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1290160 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.8529. Min Act: -0.0001

Data Index: 440178 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7261. Min Act: -0.0001

Data Index: 14170 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7457. Min Act: -0.0001

Data Index: 1152525 (C4 (Web Text))

Max Activating Token Index: 611

Text #13

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7354. Min Act: -0.0001

Data Index: 188718 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7068. Min Act: -0.0001

Data Index: 1195488 (C4 (Web Text))

Max Activating Token Index: 525

Text #15

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.6790. Min Act: -0.0001

Data Index: 68171 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.6155. Min Act: -0.0001

Data Index: 972801 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7474. Min Act: -0.0001

Data Index: 666083 (C4 (Web Text))

Max Activating Token Index: 46

Text #18

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7310. Min Act: -0.0001

Data Index: 907259 (C4 (Web Text))

Max Activating Token Index: 341

Text #19

Max Range: 0.9540. Min Range: -0.9540

Max Act: 0.7194. Min Act: -0.0001

Data Index: 462612 (C4 (Web Text))

Max Activating Token Index: 723