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

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

Neuron 2002 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1783. Min Range: -1.1783

Max Act: 1.1783. Min Act: -0.0001

Data Index: 620499 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.9589. Min Act: -0.0001

Data Index: 300431 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.8550. Min Act: -0.0001

Data Index: 30164 (C4 (Web Text))

Max Activating Token Index: 956

Text #3

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.7427. Min Act: -0.0001

Data Index: 737102 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.7390. Min Act: -0.0001

Data Index: 976210 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1275982 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.6520. Min Act: -0.0001

Data Index: 1199303 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.6502. Min Act: -0.0001

Data Index: 1261501 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.6308. Min Act: -0.0001

Data Index: 1289313 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.6047. Min Act: -0.0001

Data Index: 377432 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.6480. Min Act: -0.0001

Data Index: 319468 (C4 (Web Text))

Max Activating Token Index: 553

Text #11

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.6130. Min Act: -0.0001

Data Index: 593357 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5765. Min Act: -0.0001

Data Index: 1106330 (C4 (Web Text))

Max Activating Token Index: 168

Text #13

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5342. Min Act: -0.0001

Data Index: 850181 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5549. Min Act: -0.0001

Data Index: 1175169 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5260. Min Act: -0.0001

Data Index: 288225 (C4 (Web Text))

Max Activating Token Index: 926

Text #16

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5353. Min Act: -0.0001

Data Index: 1602652 (Python Code)

Max Activating Token Index: 30

Text #17

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5073. Min Act: -0.0001

Data Index: 989158 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5295. Min Act: -0.0001

Data Index: 603094 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 1.1783. Min Range: -1.1783

Max Act: 0.5109. Min Act: -0.0001

Data Index: 1154338 (C4 (Web Text))

Max Activating Token Index: 667