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

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

Neuron 2138 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: 0.4972. Min Range: -0.4972

Max Act: 0.4972. Min Act: 0.0000

Data Index: 1019106 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3988. Min Act: -0.0000

Data Index: 328128 (C4 (Web Text))

Max Activating Token Index: 333

Text #2

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3885. Min Act: -0.0000

Data Index: 760371 (C4 (Web Text))

Max Activating Token Index: 585

Text #3

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3672. Min Act: -0.0001

Data Index: 1137800 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3767. Min Act: 0.0001

Data Index: 1067501 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.3724. Min Act: -0.0000

Data Index: 813138 (C4 (Web Text))

Max Activating Token Index: 891

Text #6

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2884. Min Act: -0.0001

Data Index: 451464 (C4 (Web Text))

Max Activating Token Index: 637

Text #7

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2989. Min Act: -0.0000

Data Index: 265787 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2897. Min Act: -0.0000

Data Index: 696411 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2872. Min Act: -0.0001

Data Index: 241130 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2838. Min Act: -0.0000

Data Index: 1147820 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2815. Min Act: -0.0001

Data Index: 1012820 (C4 (Web Text))

Max Activating Token Index: 169

Text #12

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2724. Min Act: 0.0001

Data Index: 890569 (C4 (Web Text))

Max Activating Token Index: 567

Text #13

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2685. Min Act: -0.0000

Data Index: 385677 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2769. Min Act: -0.0000

Data Index: 1168037 (C4 (Web Text))

Max Activating Token Index: 749

Text #15

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1232289 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2705. Min Act: -0.0000

Data Index: 683281 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2738. Min Act: 0.0001

Data Index: 371782 (C4 (Web Text))

Max Activating Token Index: 479

Text #18

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2739. Min Act: -0.0000

Data Index: 1218277 (C4 (Web Text))

Max Activating Token Index: 379

Text #19

Max Range: 0.4972. Min Range: -0.4972

Max Act: 0.2658. Min Act: -0.0001

Data Index: 96527 (C4 (Web Text))

Max Activating Token Index: 159