Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2426. Min Act: -0.0001

Data Index: 846323 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2414. Min Act: -0.0001

Data Index: 722489 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2252. Min Act: -0.0001

Data Index: 1127667 (C4 (Web Text))

Max Activating Token Index: 520

Text #3

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2288. Min Act: -0.0001

Data Index: 879182 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2289. Min Act: -0.0001

Data Index: 1118764 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2212. Min Act: -0.0001

Data Index: 283147 (C4 (Web Text))

Max Activating Token Index: 536

Text #6

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2220. Min Act: -0.0001

Data Index: 238867 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2035. Min Act: -0.0001

Data Index: 849397 (C4 (Web Text))

Max Activating Token Index: 891

Text #8

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2096. Min Act: -0.0000

Data Index: 394633 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.2017. Min Act: -0.0001

Data Index: 708102 (C4 (Web Text))

Max Activating Token Index: 447

Text #10

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1991. Min Act: -0.0001

Data Index: 78901 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1928. Min Act: -0.0001

Data Index: 702191 (C4 (Web Text))

Max Activating Token Index: 419

Text #12

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1872. Min Act: -0.0001

Data Index: 131202 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1914. Min Act: -0.0001

Data Index: 294452 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1747. Min Act: -0.0001

Data Index: 1309492 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1712. Min Act: -0.0001

Data Index: 778182 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1595. Min Act: -0.0001

Data Index: 929274 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1358. Min Act: -0.0001

Data Index: 965728 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1088369 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.2426. Min Range: -0.2426

Max Act: 0.1495. Min Act: -0.0001

Data Index: 1031336 (C4 (Web Text))

Max Activating Token Index: 447