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

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

Neuron 4130 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3783. Min Range: -1.3783

Max Act: 1.3527. Min Act: -0.0001

Data Index: 345905 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.3783. Min Range: -1.3783

Max Act: 1.1791. Min Act: -0.0001

Data Index: 180742 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.3783. Min Range: -1.3783

Max Act: 1.2308. Min Act: -0.0001

Data Index: 385884 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 1.3783. Min Range: -1.3783

Max Act: 1.3783. Min Act: -0.0001

Data Index: 809673 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.3783. Min Range: -1.3783

Max Act: 1.1827. Min Act: -0.0001

Data Index: 43482 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.3783. Min Range: -1.3783

Max Act: 1.1133. Min Act: -0.0001

Data Index: 406790 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.9185. Min Act: -0.0001

Data Index: 84915 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.9522. Min Act: -0.0001

Data Index: 172099 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.8346. Min Act: -0.0001

Data Index: 176926 (C4 (Web Text))

Max Activating Token Index: 724

Text #9

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.7690. Min Act: -0.0001

Data Index: 764128 (C4 (Web Text))

Max Activating Token Index: 387

Text #10

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.9481. Min Act: -0.0001

Data Index: 146682 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.8772. Min Act: -0.0001

Data Index: 432510 (C4 (Web Text))

Max Activating Token Index: 57

Text #12

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.8598. Min Act: -0.0001

Data Index: 785387 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.8154. Min Act: -0.0001

Data Index: 571599 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.7105. Min Act: -0.0001

Data Index: 500492 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.7431. Min Act: -0.0001

Data Index: 188694 (C4 (Web Text))

Max Activating Token Index: 964

Text #16

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.7263. Min Act: -0.0001

Data Index: 1040456 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.7561. Min Act: -0.0001

Data Index: 1023901 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.7711. Min Act: -0.0001

Data Index: 1078753 (C4 (Web Text))

Max Activating Token Index: 362

Text #19

Max Range: 1.3783. Min Range: -1.3783

Max Act: 0.7976. Min Act: -0.0001

Data Index: 891571 (C4 (Web Text))

Max Activating Token Index: 1013