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

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

Neuron 604 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.5600. Min Act: -0.0000

Data Index: 147005 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.3056. Min Act: -0.0000

Data Index: 1185320 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.4260. Min Act: -0.0000

Data Index: 1354014 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.4248. Min Act: -0.0000

Data Index: 1338719 (C4 (Web Text))

Max Activating Token Index: 664

Text #4

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.9381. Min Act: -0.0000

Data Index: 1315035 (C4 (Web Text))

Max Activating Token Index: 972

Text #5

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.2466. Min Act: -0.0000

Data Index: 341220 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.2459. Min Act: -0.0000

Data Index: 17969 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.1821. Min Act: -0.0000

Data Index: 1307542 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.0293. Min Act: -0.0000

Data Index: 986418 (C4 (Web Text))

Max Activating Token Index: 888

Text #9

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.0486. Min Act: -0.0000

Data Index: 346173 (C4 (Web Text))

Max Activating Token Index: 644

Text #10

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.0460. Min Act: -0.0000

Data Index: 1027953 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.0046. Min Act: -0.0000

Data Index: 1196686 (C4 (Web Text))

Max Activating Token Index: 22

Text #12

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.9108. Min Act: -0.0000

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 4.5600. Min Range: -4.5600

Max Act: 4.1005. Min Act: -0.0000

Data Index: 701197 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.7148. Min Act: -0.0000

Data Index: 1265384 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.5186. Min Act: -0.0000

Data Index: 693046 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.8438. Min Act: -0.0000

Data Index: 1269787 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.7783. Min Act: -0.0000

Data Index: 303318 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.7514. Min Act: -0.0000

Data Index: 530640 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 4.5600. Min Range: -4.5600

Max Act: 3.5632. Min Act: -0.0000

Data Index: 385315 (C4 (Web Text))

Max Activating Token Index: 784