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

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

Neuron 3857 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.9694. Min Act: -0.0000

Data Index: 514968 (C4 (Web Text))

Max Activating Token Index: 445

Text #1

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.5398. Min Act: -0.0000

Data Index: 507242 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.6734. Min Act: -0.0000

Data Index: 528663 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.3399. Min Act: -0.0000

Data Index: 1035822 (C4 (Web Text))

Max Activating Token Index: 901

Text #4

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.3023. Min Act: -0.0000

Data Index: 963459 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.4441. Min Act: -0.0000

Data Index: 252716 (C4 (Web Text))

Max Activating Token Index: 59

Text #6

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.4340. Min Act: -0.0000

Data Index: 1132465 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.0427. Min Act: -0.0000

Data Index: 1255094 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.7502. Min Act: -0.0000

Data Index: 670432 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.7444. Min Act: -0.0000

Data Index: 653494 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.6994. Min Act: -0.0000

Data Index: 639150 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 3.9694. Min Range: -3.9694

Max Act: 3.0018. Min Act: -0.0000

Data Index: 549675 (C4 (Web Text))

Max Activating Token Index: 251

Text #12

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.9851. Min Act: -0.0000

Data Index: 1359567 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.7959. Min Act: -0.0000

Data Index: 1342747 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.8783. Min Act: -0.0000

Data Index: 587432 (C4 (Web Text))

Max Activating Token Index: 435

Text #15

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.6101. Min Act: -0.0000

Data Index: 479857 (C4 (Web Text))

Max Activating Token Index: 776

Text #16

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.7279. Min Act: -0.0000

Data Index: 973799 (C4 (Web Text))

Max Activating Token Index: 132

Text #17

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.7128. Min Act: -0.0000

Data Index: 306888 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.8582. Min Act: -0.0000

Data Index: 24445 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 3.9694. Min Range: -3.9694

Max Act: 2.8158. Min Act: -0.0000

Data Index: 809398 (C4 (Web Text))

Max Activating Token Index: 83