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

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

Neuron 987 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.6578. Min Act: -0.0000

Data Index: 21991 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.7106. Min Act: -0.0000

Data Index: 649265 (C4 (Web Text))

Max Activating Token Index: 130

Text #2

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.7739. Min Act: -0.0000

Data Index: 626002 (C4 (Web Text))

Max Activating Token Index: 100

Text #3

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.5496. Min Act: -0.0000

Data Index: 625998 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.5175. Min Act: -0.0000

Data Index: 1333734 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.5194. Min Act: -0.0000

Data Index: 537336 (C4 (Web Text))

Max Activating Token Index: 307

Text #6

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.3242. Min Act: -0.0000

Data Index: 645931 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.3069. Min Act: -0.0000

Data Index: 561868 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.4410. Min Act: -0.0000

Data Index: 1057046 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.2956. Min Act: -0.0000

Data Index: 363245 (C4 (Web Text))

Max Activating Token Index: 536

Text #10

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.1644. Min Act: -0.0000

Data Index: 49194 (C4 (Web Text))

Max Activating Token Index: 936

Text #11

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.1964. Min Act: -0.0000

Data Index: 334799 (C4 (Web Text))

Max Activating Token Index: 369

Text #12

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.2524. Min Act: -0.0000

Data Index: 734620 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.2302. Min Act: -0.0000

Data Index: 1124886 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.1403. Min Act: -0.0000

Data Index: 224985 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.2860. Min Act: -0.0000

Data Index: 1323539 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.1373. Min Act: -0.0000

Data Index: 377760 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1044487 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.1824. Min Act: -0.0000

Data Index: 1195057 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 1.7739. Min Range: -1.7739

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1197814 (C4 (Web Text))

Max Activating Token Index: 439