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

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

Neuron 1416 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5589. Min Act: -0.0003

Data Index: 1002645 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.5122. Min Act: -0.0002

Data Index: 335073 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4440. Min Act: -0.0003

Data Index: 657444 (C4 (Web Text))

Max Activating Token Index: 749

Text #3

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3993. Min Act: -0.0002

Data Index: 524146 (C4 (Web Text))

Max Activating Token Index: 159

Text #4

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3890. Min Act: -0.0003

Data Index: 359901 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.4040. Min Act: -0.0002

Data Index: 605702 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3519. Min Act: -0.0003

Data Index: 951641 (C4 (Web Text))

Max Activating Token Index: 686

Text #7

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3668. Min Act: -0.0003

Data Index: 1217154 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3537. Min Act: -0.0002

Data Index: 395593 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3469. Min Act: -0.0003

Data Index: 712313 (C4 (Web Text))

Max Activating Token Index: 690

Text #10

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3288. Min Act: -0.0002

Data Index: 569956 (C4 (Web Text))

Max Activating Token Index: 918

Text #11

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2965. Min Act: -0.0002

Data Index: 966217 (C4 (Web Text))

Max Activating Token Index: 456

Text #12

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3135. Min Act: -0.0003

Data Index: 939347 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3072. Min Act: -0.0002

Data Index: 551811 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2865. Min Act: -0.0003

Data Index: 320610 (C4 (Web Text))

Max Activating Token Index: 509

Text #15

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3068. Min Act: -0.0003

Data Index: 18581 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3062. Min Act: -0.0002

Data Index: 1190176 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.3016. Min Act: -0.0003

Data Index: 501554 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2934. Min Act: -0.0002

Data Index: 18472 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 0.5589. Min Range: -0.5589

Max Act: 0.2754. Min Act: -0.0002

Data Index: 429060 (C4 (Web Text))

Max Activating Token Index: 12