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

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

Neuron 1372 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: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1024510 (C4 (Web Text))

Max Activating Token Index: 234

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0571. Min Act: -0.0002

Data Index: 44006 (C4 (Web Text))

Max Activating Token Index: 353

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1040974 (C4 (Web Text))

Max Activating Token Index: 505

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0573. Min Act: -0.0002

Data Index: 609129 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1020960 (C4 (Web Text))

Max Activating Token Index: 79

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0573. Min Act: -0.0002

Data Index: 876201 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1216320 (C4 (Web Text))

Max Activating Token Index: 491

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0560. Min Act: -0.0002

Data Index: 743073 (C4 (Web Text))

Max Activating Token Index: 965

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0558. Min Act: -0.0002

Data Index: 895946 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1456344 (Python Code)

Max Activating Token Index: 79

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0524. Min Act: -0.0002

Data Index: 793882 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0482. Min Act: -0.0002

Data Index: 1202734 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0495. Min Act: -0.0002

Data Index: 232981 (C4 (Web Text))

Max Activating Token Index: 657

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0489. Min Act: -0.0002

Data Index: 1560634 (Python Code)

Max Activating Token Index: 762

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0456. Min Act: -0.0002

Data Index: 302068 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1164495 (C4 (Web Text))

Max Activating Token Index: 797

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0473. Min Act: -0.0002

Data Index: 300941 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0476. Min Act: -0.0002

Data Index: 674204 (C4 (Web Text))

Max Activating Token Index: 144

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0470. Min Act: -0.0002

Data Index: 821397 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0455. Min Act: -0.0002

Data Index: 1444674 (Python Code)

Max Activating Token Index: 862