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

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

Neuron 3803 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.8020. Min Act: -0.0000

Data Index: 735093 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7282. Min Act: -0.0000

Data Index: 220603 (C4 (Web Text))

Max Activating Token Index: 376

Text #2

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7003. Min Act: -0.0000

Data Index: 1308672 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7188. Min Act: -0.0000

Data Index: 220201 (C4 (Web Text))

Max Activating Token Index: 451

Text #4

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7600. Min Act: -0.0000

Data Index: 378953 (C4 (Web Text))

Max Activating Token Index: 933

Text #5

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6689. Min Act: -0.0000

Data Index: 383420 (C4 (Web Text))

Max Activating Token Index: 243

Text #6

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7022. Min Act: -0.0000

Data Index: 984976 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7207. Min Act: -0.0000

Data Index: 1013290 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6834. Min Act: -0.0000

Data Index: 287153 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7325. Min Act: -0.0000

Data Index: 147509 (C4 (Web Text))

Max Activating Token Index: 216

Text #10

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1274153 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1538326 (Python Code)

Max Activating Token Index: 856

Text #12

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6754. Min Act: -0.0000

Data Index: 521488 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.7595. Min Act: -0.0000

Data Index: 159918 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6877. Min Act: -0.0000

Data Index: 838729 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6910. Min Act: -0.0000

Data Index: 630847 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6882. Min Act: -0.0000

Data Index: 140025 (C4 (Web Text))

Max Activating Token Index: 969

Text #17

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1332710 (C4 (Web Text))

Max Activating Token Index: 596

Text #18

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6714. Min Act: -0.0000

Data Index: 619466 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.8020. Min Range: -0.8020

Max Act: 0.6736. Min Act: -0.0000

Data Index: 43023 (C4 (Web Text))

Max Activating Token Index: 423