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

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

Neuron 3100 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4852. Min Act: -0.0000

Data Index: 165638 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1089719 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4514. Min Act: -0.0000

Data Index: 1049315 (C4 (Web Text))

Max Activating Token Index: 493

Text #3

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4376. Min Act: -0.0000

Data Index: 539084 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4261. Min Act: -0.0000

Data Index: 935364 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4070. Min Act: -0.0000

Data Index: 1261667 (C4 (Web Text))

Max Activating Token Index: 399

Text #6

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4036. Min Act: -0.0000

Data Index: 821714 (C4 (Web Text))

Max Activating Token Index: 406

Text #7

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.4068. Min Act: 0.0001

Data Index: 379910 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1034378 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3768. Min Act: -0.0000

Data Index: 969361 (C4 (Web Text))

Max Activating Token Index: 956

Text #10

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1571442 (Python Code)

Max Activating Token Index: 299

Text #11

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3946. Min Act: -0.0000

Data Index: 796719 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3828. Min Act: -0.0000

Data Index: 413494 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3640. Min Act: -0.0000

Data Index: 1340914 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3869. Min Act: -0.0000

Data Index: 1326326 (C4 (Web Text))

Max Activating Token Index: 996

Text #15

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3892. Min Act: 0.0000

Data Index: 1209883 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3824. Min Act: -0.0000

Data Index: 588292 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3605. Min Act: -0.0000

Data Index: 316903 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3738. Min Act: -0.0000

Data Index: 171347 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.4905. Min Range: -0.4905

Max Act: 0.3749. Min Act: 0.0000

Data Index: 606714 (C4 (Web Text))

Max Activating Token Index: 900