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

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

Neuron 2570 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: 924550 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0512. Min Act: -0.0002

Data Index: 1263413 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1026797 (C4 (Web Text))

Max Activating Token Index: 345

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0502. Min Act: -0.0002

Data Index: 266297 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0495. Min Act: -0.0002

Data Index: 172046 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0499. Min Act: -0.0002

Data Index: 88259 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1277886 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0505. Min Act: -0.0002

Data Index: 931499 (C4 (Web Text))

Max Activating Token Index: 462

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0516. Min Act: -0.0002

Data Index: 68022 (C4 (Web Text))

Max Activating Token Index: 296

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0489. Min Act: -0.0002

Data Index: 889252 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0469. Min Act: -0.0002

Data Index: 233871 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0475. Min Act: -0.0002

Data Index: 909044 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0478. Min Act: -0.0002

Data Index: 853600 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0468. Min Act: -0.0002

Data Index: 1212466 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1172155 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0459. Min Act: -0.0002

Data Index: 601463 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0468. Min Act: -0.0002

Data Index: 110708 (C4 (Web Text))

Max Activating Token Index: 984

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0457. Min Act: -0.0002

Data Index: 836924 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0454. Min Act: -0.0002

Data Index: 1231573 (C4 (Web Text))

Max Activating Token Index: 367

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0456. Min Act: -0.0002

Data Index: 961501 (C4 (Web Text))

Max Activating Token Index: 605