Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 629 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1101305 (C4 (Web Text))

Max Activating Token Index: 257

Text #1

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5571. Min Act: -0.0000

Data Index: 226301 (C4 (Web Text))

Max Activating Token Index: 614

Text #2

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5434. Min Act: -0.0001

Data Index: 591369 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5297. Min Act: -0.0000

Data Index: 634833 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4901. Min Act: -0.0000

Data Index: 62721 (C4 (Web Text))

Max Activating Token Index: 893

Text #5

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5316. Min Act: -0.0001

Data Index: 647892 (C4 (Web Text))

Max Activating Token Index: 946

Text #6

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4998. Min Act: -0.0000

Data Index: 296786 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.5042. Min Act: -0.0001

Data Index: 23741 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4906. Min Act: -0.0000

Data Index: 308344 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4796. Min Act: -0.0000

Data Index: 470664 (C4 (Web Text))

Max Activating Token Index: 845

Text #10

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4895. Min Act: -0.0000

Data Index: 1216565 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4820. Min Act: -0.0001

Data Index: 666313 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4835. Min Act: -0.0000

Data Index: 520062 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4725. Min Act: -0.0000

Data Index: 171758 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4709. Min Act: -0.0001

Data Index: 1233137 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4485. Min Act: -0.0000

Data Index: 893808 (C4 (Web Text))

Max Activating Token Index: 883

Text #16

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4621. Min Act: -0.0000

Data Index: 1086961 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4459. Min Act: -0.0001

Data Index: 121535 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4427. Min Act: -0.0000

Data Index: 834768 (C4 (Web Text))

Max Activating Token Index: 281

Text #19

Max Range: 0.5769. Min Range: -0.5769

Max Act: 0.4395. Min Act: -0.0001

Data Index: 596791 (C4 (Web Text))

Max Activating Token Index: 800