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

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

Neuron 534 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0001

Data Index: 839853 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0888. Min Act: -0.0001

Data Index: 136265 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0893. Min Act: -0.0000

Data Index: 921908 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0825. Min Act: -0.0001

Data Index: 725930 (C4 (Web Text))

Max Activating Token Index: 658

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0833. Min Act: -0.0001

Data Index: 800565 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0853. Min Act: -0.0001

Data Index: 102194 (C4 (Web Text))

Max Activating Token Index: 341

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0792. Min Act: -0.0001

Data Index: 1246664 (C4 (Web Text))

Max Activating Token Index: 498

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0781. Min Act: -0.0000

Data Index: 11676 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0791. Min Act: -0.0000

Data Index: 89501 (C4 (Web Text))

Max Activating Token Index: 463

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0787. Min Act: -0.0001

Data Index: 28190 (C4 (Web Text))

Max Activating Token Index: 251

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0747. Min Act: -0.0001

Data Index: 754615 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0818. Min Act: -0.0001

Data Index: 954017 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0779. Min Act: -0.0001

Data Index: 243473 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0818. Min Act: -0.0000

Data Index: 620823 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0768. Min Act: -0.0001

Data Index: 865025 (C4 (Web Text))

Max Activating Token Index: 331

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0766. Min Act: -0.0001

Data Index: 638461 (C4 (Web Text))

Max Activating Token Index: 584

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0793. Min Act: -0.0001

Data Index: 252863 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1003331 (C4 (Web Text))

Max Activating Token Index: 487

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0772. Min Act: -0.0001

Data Index: 583101 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1340228 (C4 (Web Text))

Max Activating Token Index: 855