Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 462 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.3113. Min Act: -0.0000

Data Index: 937441 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2594. Min Act: -0.0001

Data Index: 656494 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2442. Min Act: -0.0001

Data Index: 789607 (C4 (Web Text))

Max Activating Token Index: 322

Text #3

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2424. Min Act: -0.0001

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2511. Min Act: -0.0001

Data Index: 439642 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2374. Min Act: -0.0001

Data Index: 535923 (C4 (Web Text))

Max Activating Token Index: 244

Text #6

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2233. Min Act: -0.0001

Data Index: 293941 (C4 (Web Text))

Max Activating Token Index: 246

Text #7

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2219. Min Act: -0.0000

Data Index: 616781 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1967. Min Act: -0.0001

Data Index: 110331 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2281. Min Act: -0.0000

Data Index: 853357 (C4 (Web Text))

Max Activating Token Index: 660

Text #10

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2190. Min Act: -0.0000

Data Index: 379849 (C4 (Web Text))

Max Activating Token Index: 648

Text #11

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2069. Min Act: -0.0001

Data Index: 1250155 (C4 (Web Text))

Max Activating Token Index: 911

Text #12

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2133. Min Act: -0.0000

Data Index: 630308 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2025. Min Act: -0.0000

Data Index: 490814 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2241. Min Act: -0.0000

Data Index: 555741 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2130. Min Act: -0.0000

Data Index: 277105 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2016. Min Act: -0.0000

Data Index: 88601 (C4 (Web Text))

Max Activating Token Index: 461

Text #17

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.2058. Min Act: -0.0000

Data Index: 370951 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1975. Min Act: -0.0001

Data Index: 760012 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.3113. Min Range: -0.3113

Max Act: 0.1882. Min Act: -0.0000

Data Index: 921614 (C4 (Web Text))

Max Activating Token Index: 163