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

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

Neuron 5677 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: 4.3314. Min Range: -4.3314

Max Act: 4.3314. Min Act: -0.0000

Data Index: 121009 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 4.3314. Min Range: -4.3314

Max Act: 4.2150. Min Act: -0.0000

Data Index: 891459 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 4.3314. Min Range: -4.3314

Max Act: 4.1714. Min Act: -0.0000

Data Index: 1072254 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 4.3314. Min Range: -4.3314

Max Act: 4.1553. Min Act: -0.0000

Data Index: 1262993 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 4.3314. Min Range: -4.3314

Max Act: 4.2985. Min Act: -0.0000

Data Index: 741294 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 4.3314. Min Range: -4.3314

Max Act: 4.0917. Min Act: -0.0000

Data Index: 1275231 (C4 (Web Text))

Max Activating Token Index: 461

Text #6

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.9896. Min Act: -0.0000

Data Index: 1326886 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.6313. Min Act: -0.0000

Data Index: 383867 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.5427. Min Act: -0.0000

Data Index: 583219 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.5379. Min Act: -0.0000

Data Index: 494550 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.6683. Min Act: -0.0000

Data Index: 1073145 (C4 (Web Text))

Max Activating Token Index: 93

Text #11

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.5603. Min Act: -0.0000

Data Index: 279128 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.5153. Min Act: -0.0000

Data Index: 1072012 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.0028. Min Act: -0.0000

Data Index: 1331320 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.3991. Min Act: -0.0000

Data Index: 1078182 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.2391. Min Act: -0.0000

Data Index: 205288 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 4.3314. Min Range: -4.3314

Max Act: 2.7154. Min Act: -0.0000

Data Index: 1221341 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.1849. Min Act: -0.0000

Data Index: 424961 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.0124. Min Act: -0.0000

Data Index: 597429 (C4 (Web Text))

Max Activating Token Index: 997

Text #19

Max Range: 4.3314. Min Range: -4.3314

Max Act: 3.0114. Min Act: -0.0000

Data Index: 8138 (C4 (Web Text))

Max Activating Token Index: 145