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

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

Neuron 2878 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: 0.4155. Min Range: -0.4155

Max Act: 0.4155. Min Act: -0.0000

Data Index: 322050 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3752. Min Act: -0.0001

Data Index: 1203145 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3788. Min Act: -0.0001

Data Index: 800863 (C4 (Web Text))

Max Activating Token Index: 850

Text #3

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3298. Min Act: -0.0001

Data Index: 374316 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3304. Min Act: -0.0000

Data Index: 656226 (C4 (Web Text))

Max Activating Token Index: 865

Text #5

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3333. Min Act: -0.0001

Data Index: 935721 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3176. Min Act: -0.0001

Data Index: 1108356 (C4 (Web Text))

Max Activating Token Index: 339

Text #7

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3265. Min Act: -0.0000

Data Index: 800641 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2950. Min Act: -0.0001

Data Index: 766194 (C4 (Web Text))

Max Activating Token Index: 678

Text #9

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3230. Min Act: -0.0001

Data Index: 1531284 (Python Code)

Max Activating Token Index: 251

Text #10

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3480. Min Act: -0.0001

Data Index: 182380 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3132. Min Act: -0.0001

Data Index: 1646095 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3371. Min Act: -0.0000

Data Index: 487123 (C4 (Web Text))

Max Activating Token Index: 979

Text #13

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3035. Min Act: -0.0001

Data Index: 1253505 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2816. Min Act: -0.0000

Data Index: 584621 (C4 (Web Text))

Max Activating Token Index: 969

Text #15

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3130. Min Act: -0.0001

Data Index: 622907 (C4 (Web Text))

Max Activating Token Index: 860

Text #16

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.3098. Min Act: -0.0001

Data Index: 332587 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2988. Min Act: -0.0001

Data Index: 11862 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2979. Min Act: -0.0001

Data Index: 1528411 (Python Code)

Max Activating Token Index: 309

Text #19

Max Range: 0.4155. Min Range: -0.4155

Max Act: 0.2837. Min Act: -0.0001

Data Index: 1424997 (Python Code)

Max Activating Token Index: 890