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

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

Neuron 2664 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.7340. Min Act: -0.0000

Data Index: 1318296 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.6743. Min Act: -0.0000

Data Index: 810241 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.6613. Min Act: -0.0000

Data Index: 191440 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.6069. Min Act: -0.0000

Data Index: 1266253 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5982. Min Act: -0.0000

Data Index: 521941 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.6129. Min Act: -0.0000

Data Index: 545320 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5684. Min Act: -0.0000

Data Index: 1238040 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5499. Min Act: -0.0000

Data Index: 627075 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5319. Min Act: -0.0000

Data Index: 186405 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5713. Min Act: -0.0000

Data Index: 494007 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1315717 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.6044. Min Act: -0.0000

Data Index: 513964 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5902. Min Act: -0.0000

Data Index: 984655 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5666. Min Act: -0.0000

Data Index: 576759 (C4 (Web Text))

Max Activating Token Index: 715

Text #14

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5815. Min Act: -0.0000

Data Index: 956686 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.6140. Min Act: -0.0000

Data Index: 899282 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5873. Min Act: -0.0000

Data Index: 1340970 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.6116. Min Act: -0.0000

Data Index: 637155 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5736. Min Act: -0.0000

Data Index: 512309 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.7340. Min Range: -0.7340

Max Act: 0.5681. Min Act: -0.0000

Data Index: 53558 (C4 (Web Text))

Max Activating Token Index: 403