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

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

Neuron 2128 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8744. Min Act: -0.0001

Data Index: 247062 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8355. Min Act: -0.0001

Data Index: 988086 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8236. Min Act: -0.0001

Data Index: 1081742 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.8290. Min Act: -0.0001

Data Index: 1083308 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7433. Min Act: -0.0001

Data Index: 27741 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6501. Min Act: -0.0001

Data Index: 917748 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7308. Min Act: -0.0001

Data Index: 503246 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6770. Min Act: -0.0001

Data Index: 226985 (C4 (Web Text))

Max Activating Token Index: 968

Text #8

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6738. Min Act: -0.0001

Data Index: 740778 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6916. Min Act: -0.0001

Data Index: 216764 (C4 (Web Text))

Max Activating Token Index: 64

Text #10

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.7238. Min Act: -0.0001

Data Index: 147585 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6293. Min Act: -0.0001

Data Index: 540615 (C4 (Web Text))

Max Activating Token Index: 705

Text #12

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6933. Min Act: -0.0001

Data Index: 1025542 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6291. Min Act: -0.0001

Data Index: 1322505 (C4 (Web Text))

Max Activating Token Index: 721

Text #14

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6402. Min Act: -0.0001

Data Index: 567616 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6341. Min Act: -0.0001

Data Index: 821317 (C4 (Web Text))

Max Activating Token Index: 478

Text #16

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6317. Min Act: -0.0001

Data Index: 1156120 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.6048. Min Act: -0.0001

Data Index: 96134 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5733. Min Act: -0.0001

Data Index: 77408 (C4 (Web Text))

Max Activating Token Index: 974

Text #19

Max Range: 0.8744. Min Range: -0.8744

Max Act: 0.5901. Min Act: -0.0001

Data Index: 577854 (C4 (Web Text))

Max Activating Token Index: 397