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

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

Neuron 6106 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: 0.7844. Min Range: -0.7844

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1650381 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6633. Min Act: -0.0000

Data Index: 573203 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.6361. Min Act: -0.0000

Data Index: 1424814 (Python Code)

Max Activating Token Index: 221

Text #3

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1488951 (Python Code)

Max Activating Token Index: 647

Text #4

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5103. Min Act: -0.0000

Data Index: 1317143 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1377943 (Python Code)

Max Activating Token Index: 490

Text #6

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5246. Min Act: -0.0000

Data Index: 496366 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1246157 (C4 (Web Text))

Max Activating Token Index: 695

Text #8

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4956. Min Act: -0.0000

Data Index: 1602806 (Python Code)

Max Activating Token Index: 89

Text #9

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4862. Min Act: -0.0000

Data Index: 453541 (C4 (Web Text))

Max Activating Token Index: 373

Text #10

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1583713 (Python Code)

Max Activating Token Index: 909

Text #11

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4697. Min Act: -0.0000

Data Index: 871650 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4814. Min Act: -0.0000

Data Index: 1468510 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4615. Min Act: -0.0000

Data Index: 287060 (C4 (Web Text))

Max Activating Token Index: 230

Text #14

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4951. Min Act: -0.0000

Data Index: 650537 (C4 (Web Text))

Max Activating Token Index: 563

Text #15

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4413. Min Act: -0.0000

Data Index: 225044 (C4 (Web Text))

Max Activating Token Index: 521

Text #16

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1605563 (Python Code)

Max Activating Token Index: 64

Text #17

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4390. Min Act: -0.0000

Data Index: 775849 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1553778 (Python Code)

Max Activating Token Index: 365

Text #19

Max Range: 0.7844. Min Range: -0.7844

Max Act: 0.4675. Min Act: -0.0000

Data Index: 302119 (C4 (Web Text))

Max Activating Token Index: 485