Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5900 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.1103. Min Act: -0.0002

Data Index: 929650 (C4 (Web Text))

Max Activating Token Index: 112

Text #1

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0858. Min Act: -0.0002

Data Index: 524481 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0825. Min Act: -0.0002

Data Index: 520500 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0829. Min Act: -0.0002

Data Index: 228716 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0808. Min Act: -0.0002

Data Index: 960047 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0769. Min Act: -0.0002

Data Index: 796863 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1077251 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0787. Min Act: -0.0002

Data Index: 1131471 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0786. Min Act: -0.0002

Data Index: 819788 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0781. Min Act: -0.0002

Data Index: 699587 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0788. Min Act: -0.0002

Data Index: 344042 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0775. Min Act: -0.0002

Data Index: 201470 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0775. Min Act: -0.0002

Data Index: 653438 (C4 (Web Text))

Max Activating Token Index: 347

Text #13

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0738. Min Act: -0.0002

Data Index: 250696 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0756. Min Act: -0.0002

Data Index: 1017997 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0756. Min Act: -0.0002

Data Index: 853224 (C4 (Web Text))

Max Activating Token Index: 470

Text #16

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1336462 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0739. Min Act: -0.0002

Data Index: 436457 (C4 (Web Text))

Max Activating Token Index: 432

Text #18

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0728. Min Act: -0.0002

Data Index: 539910 (C4 (Web Text))

Max Activating Token Index: 676

Text #19

Max Range: 0.1103. Min Range: -0.1103

Max Act: 0.0722. Min Act: -0.0002

Data Index: 264046 (C4 (Web Text))

Max Activating Token Index: 685