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

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

Neuron 2474 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.0776. Min Act: -0.0000

Data Index: 481558 (C4 (Web Text))

Max Activating Token Index: 822

Text #1

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.1773. Min Act: -0.0000

Data Index: 494645 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 4.2050. Min Range: -4.2050

Max Act: 4.2050. Min Act: -0.0000

Data Index: 158982 (C4 (Web Text))

Max Activating Token Index: 922

Text #3

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.5147. Min Act: -0.0000

Data Index: 173646 (C4 (Web Text))

Max Activating Token Index: 781

Text #4

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.6497. Min Act: -0.0000

Data Index: 793384 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9018. Min Act: -0.0000

Data Index: 507956 (C4 (Web Text))

Max Activating Token Index: 859

Text #6

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.8889. Min Act: -0.0000

Data Index: 569746 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.8648. Min Act: -0.0000

Data Index: 294481 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.6471. Min Act: -0.0000

Data Index: 1143444 (C4 (Web Text))

Max Activating Token Index: 431

Text #9

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.6317. Min Act: -0.0000

Data Index: 713462 (C4 (Web Text))

Max Activating Token Index: 971

Text #10

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.8798. Min Act: -0.0000

Data Index: 128572 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.7489. Min Act: -0.0000

Data Index: 793691 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.5680. Min Act: -0.0000

Data Index: 436247 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.7232. Min Act: -0.0000

Data Index: 924294 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.2226. Min Act: -0.0000

Data Index: 587359 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.3770. Min Act: -0.0000

Data Index: 290751 (C4 (Web Text))

Max Activating Token Index: 211

Text #16

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.6913. Min Act: -0.0000

Data Index: 480861 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.9785. Min Act: -0.0000

Data Index: 1191861 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.6369. Min Act: -0.0000

Data Index: 1048911 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 4.2050. Min Range: -4.2050

Max Act: 3.4000. Min Act: -0.0000

Data Index: 588827 (C4 (Web Text))

Max Activating Token Index: 126