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

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

Neuron 3403 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: 59917 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0561. Min Act: -0.0002

Data Index: 915784 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0528. Min Act: -0.0002

Data Index: 699263 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0523. Min Act: -0.0002

Data Index: 917106 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0502. Min Act: -0.0002

Data Index: 889591 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0489. Min Act: -0.0002

Data Index: 791102 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0494. Min Act: -0.0002

Data Index: 298487 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0481. Min Act: -0.0002

Data Index: 802022 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0453. Min Act: -0.0002

Data Index: 1265578 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0446. Min Act: -0.0002

Data Index: 234113 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0464. Min Act: -0.0002

Data Index: 1053044 (C4 (Web Text))

Max Activating Token Index: 737

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0454. Min Act: -0.0002

Data Index: 304312 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0442. Min Act: -0.0002

Data Index: 891624 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0410. Min Act: -0.0002

Data Index: 874953 (C4 (Web Text))

Max Activating Token Index: 290

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0441. Min Act: -0.0002

Data Index: 130761 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0408. Min Act: -0.0002

Data Index: 402649 (C4 (Web Text))

Max Activating Token Index: 313

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0441. Min Act: -0.0002

Data Index: 463315 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0424. Min Act: -0.0002

Data Index: 408706 (C4 (Web Text))

Max Activating Token Index: 532

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0421. Min Act: -0.0002

Data Index: 126139 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0436. Min Act: -0.0002

Data Index: 69753 (C4 (Web Text))

Max Activating Token Index: 266