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

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

Neuron 3633 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1332. Min Act: -0.0000

Data Index: 784065 (C4 (Web Text))

Max Activating Token Index: 792

Text #1

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1348. Min Act: -0.0000

Data Index: 948565 (C4 (Web Text))

Max Activating Token Index: 475

Text #2

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.1152. Min Act: -0.0000

Data Index: 706806 (C4 (Web Text))

Max Activating Token Index: 962

Text #3

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0815. Min Act: -0.0000

Data Index: 142026 (C4 (Web Text))

Max Activating Token Index: 739

Text #4

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1054988 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0790. Min Act: -0.0000

Data Index: 583586 (C4 (Web Text))

Max Activating Token Index: 236

Text #6

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0619. Min Act: -0.0000

Data Index: 185264 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0737. Min Act: -0.0000

Data Index: 1021291 (C4 (Web Text))

Max Activating Token Index: 141

Text #8

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0923. Min Act: -0.0000

Data Index: 611760 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0891. Min Act: -0.0000

Data Index: 939378 (C4 (Web Text))

Max Activating Token Index: 398

Text #10

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1041653 (C4 (Web Text))

Max Activating Token Index: 634

Text #11

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0691. Min Act: -0.0000

Data Index: 20033 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1039267 (C4 (Web Text))

Max Activating Token Index: 619

Text #13

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0688. Min Act: -0.0000

Data Index: 732223 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0620. Min Act: -0.0000

Data Index: 477158 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1205357 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0632. Min Act: -0.0000

Data Index: 5031 (C4 (Web Text))

Max Activating Token Index: 629

Text #17

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0657. Min Act: -0.0000

Data Index: 387258 (C4 (Web Text))

Max Activating Token Index: 403

Text #18

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0520. Min Act: -0.0000

Data Index: 1053153 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.1348. Min Range: -0.1348

Max Act: 0.0547. Min Act: -0.0000

Data Index: 189847 (C4 (Web Text))

Max Activating Token Index: 199