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

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

Neuron 3062 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3093. Min Range: -2.3093

Max Act: 2.2571. Min Act: -0.0000

Data Index: 336094 (C4 (Web Text))

Max Activating Token Index: 477

Text #1

Max Range: 2.3093. Min Range: -2.3093

Max Act: 2.3093. Min Act: -0.0000

Data Index: 1325560 (C4 (Web Text))

Max Activating Token Index: 281

Text #2

Max Range: 2.3093. Min Range: -2.3093

Max Act: 2.0512. Min Act: -0.0000

Data Index: 1228269 (C4 (Web Text))

Max Activating Token Index: 613

Text #3

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.9062. Min Act: -0.0000

Data Index: 310516 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.6570. Min Act: -0.0000

Data Index: 791131 (C4 (Web Text))

Max Activating Token Index: 356

Text #5

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.7256. Min Act: -0.0000

Data Index: 960714 (C4 (Web Text))

Max Activating Token Index: 496

Text #6

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.7283. Min Act: -0.0000

Data Index: 99482 (C4 (Web Text))

Max Activating Token Index: 405

Text #7

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.6695. Min Act: -0.0000

Data Index: 750844 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.7097. Min Act: -0.0000

Data Index: 236018 (C4 (Web Text))

Max Activating Token Index: 794

Text #9

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.5323. Min Act: -0.0000

Data Index: 63710 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.6465. Min Act: -0.0000

Data Index: 1214153 (C4 (Web Text))

Max Activating Token Index: 873

Text #11

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.4772. Min Act: -0.0000

Data Index: 477202 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.5298. Min Act: -0.0000

Data Index: 922385 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.7055. Min Act: -0.0000

Data Index: 106776 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.6633. Min Act: -0.0000

Data Index: 452168 (C4 (Web Text))

Max Activating Token Index: 423

Text #15

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.6697. Min Act: -0.0000

Data Index: 554440 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.5498. Min Act: -0.0000

Data Index: 507661 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.4292. Min Act: -0.0000

Data Index: 329305 (C4 (Web Text))

Max Activating Token Index: 563

Text #18

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.6160. Min Act: -0.0000

Data Index: 719245 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 2.3093. Min Range: -2.3093

Max Act: 1.6308. Min Act: -0.0000

Data Index: 1090007 (C4 (Web Text))

Max Activating Token Index: 240