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

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

Neuron 1855 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: 0.3456. Min Range: -0.3456

Max Act: 0.3456. Min Act: -0.0000

Data Index: 759075 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.3390. Min Act: -0.0000

Data Index: 337528 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2832. Min Act: -0.0000

Data Index: 740319 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2699. Min Act: -0.0000

Data Index: 866384 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2821. Min Act: -0.0001

Data Index: 1170677 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2453. Min Act: -0.0000

Data Index: 570367 (C4 (Web Text))

Max Activating Token Index: 165

Text #6

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2226. Min Act: -0.0000

Data Index: 1124059 (C4 (Web Text))

Max Activating Token Index: 446

Text #7

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2276. Min Act: -0.0001

Data Index: 254286 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2053. Min Act: -0.0001

Data Index: 812357 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2017. Min Act: -0.0000

Data Index: 1247573 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1932. Min Act: -0.0000

Data Index: 1347262 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.2051. Min Act: -0.0000

Data Index: 1580311 (Python Code)

Max Activating Token Index: 343

Text #12

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1948. Min Act: -0.0000

Data Index: 975935 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1921. Min Act: -0.0000

Data Index: 1594333 (Python Code)

Max Activating Token Index: 287

Text #14

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1913. Min Act: -0.0001

Data Index: 983470 (C4 (Web Text))

Max Activating Token Index: 278

Text #15

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1906. Min Act: -0.0000

Data Index: 312356 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1954. Min Act: -0.0000

Data Index: 1061981 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1877. Min Act: -0.0000

Data Index: 405671 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1929. Min Act: -0.0000

Data Index: 130438 (C4 (Web Text))

Max Activating Token Index: 600

Text #19

Max Range: 0.3456. Min Range: -0.3456

Max Act: 0.1861. Min Act: -0.0000

Data Index: 994426 (C4 (Web Text))

Max Activating Token Index: 391