Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2177 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7999. Min Act: -0.0000

Data Index: 629402 (C4 (Web Text))

Max Activating Token Index: 773

Text #1

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7604. Min Act: -0.0000

Data Index: 46840 (C4 (Web Text))

Max Activating Token Index: 955

Text #2

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7614. Min Act: -0.0000

Data Index: 524026 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6831. Min Act: -0.0000

Data Index: 1285170 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7501. Min Act: -0.0000

Data Index: 571278 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.7034. Min Act: -0.0000

Data Index: 771607 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6607. Min Act: -0.0000

Data Index: 201596 (C4 (Web Text))

Max Activating Token Index: 973

Text #7

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6382. Min Act: -0.0000

Data Index: 721874 (C4 (Web Text))

Max Activating Token Index: 330

Text #8

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6328. Min Act: -0.0000

Data Index: 1258806 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6437. Min Act: -0.0000

Data Index: 818954 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6277. Min Act: -0.0000

Data Index: 1244023 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6108. Min Act: -0.0000

Data Index: 972094 (C4 (Web Text))

Max Activating Token Index: 505

Text #12

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6044. Min Act: -0.0000

Data Index: 999908 (C4 (Web Text))

Max Activating Token Index: 898

Text #13

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6266. Min Act: -0.0000

Data Index: 699562 (C4 (Web Text))

Max Activating Token Index: 68

Text #14

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1237061 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6171. Min Act: -0.0000

Data Index: 512491 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6078. Min Act: -0.0000

Data Index: 819395 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1071591 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.6233. Min Act: -0.0000

Data Index: 54119 (C4 (Web Text))

Max Activating Token Index: 698

Text #19

Max Range: 0.7999. Min Range: -0.7999

Max Act: 0.5657. Min Act: -0.0000

Data Index: 993676 (C4 (Web Text))

Max Activating Token Index: 475