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

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

Neuron 1482 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.0125. Min Range: -4.0125

Max Act: 4.0125. Min Act: -0.0001

Data Index: 1013866 (C4 (Web Text))

Max Activating Token Index: 363

Text #1

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.9589. Min Act: -0.0001

Data Index: 306040 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.7097. Min Act: -0.0001

Data Index: 1156858 (C4 (Web Text))

Max Activating Token Index: 256

Text #3

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.7425. Min Act: -0.0001

Data Index: 225588 (C4 (Web Text))

Max Activating Token Index: 274

Text #4

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.6528. Min Act: -0.0001

Data Index: 687539 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.5223. Min Act: -0.0001

Data Index: 510874 (C4 (Web Text))

Max Activating Token Index: 350

Text #6

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.5532. Min Act: -0.0001

Data Index: 683850 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.1943. Min Act: -0.0001

Data Index: 106355 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.5939. Min Act: -0.0001

Data Index: 810094 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.5636. Min Act: -0.0001

Data Index: 128972 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.5885. Min Act: -0.0001

Data Index: 302972 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.2985. Min Act: -0.0001

Data Index: 455627 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.5472. Min Act: -0.0001

Data Index: 462497 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.5344. Min Act: -0.0001

Data Index: 635714 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.3704. Min Act: -0.0001

Data Index: 867432 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.3248. Min Act: -0.0001

Data Index: 1131299 (C4 (Web Text))

Max Activating Token Index: 44

Text #16

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.3141. Min Act: -0.0001

Data Index: 828851 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.2751. Min Act: -0.0001

Data Index: 1092658 (C4 (Web Text))

Max Activating Token Index: 609

Text #18

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.2574. Min Act: -0.0001

Data Index: 143958 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 4.0125. Min Range: -4.0125

Max Act: 3.3745. Min Act: -0.0001

Data Index: 151159 (C4 (Web Text))

Max Activating Token Index: 472