Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2880 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9962. Min Act: -0.0001

Data Index: 17171 (C4 (Web Text))

Max Activating Token Index: 732

Text #1

Max Range: 1.0030. Min Range: -1.0030

Max Act: 1.0030. Min Act: -0.0001

Data Index: 1468127 (Python Code)

Max Activating Token Index: 574

Text #2

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8449. Min Act: -0.0001

Data Index: 1487025 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8558. Min Act: -0.0001

Data Index: 455960 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7471. Min Act: -0.0001

Data Index: 1649435 (Python Code)

Max Activating Token Index: 919

Text #5

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7824. Min Act: -0.0001

Data Index: 1467835 (Python Code)

Max Activating Token Index: 920

Text #6

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9028. Min Act: -0.0001

Data Index: 1408540 (Python Code)

Max Activating Token Index: 554

Text #7

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7996. Min Act: -0.0001

Data Index: 1455670 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7922. Min Act: -0.0001

Data Index: 1614756 (Python Code)

Max Activating Token Index: 813

Text #9

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8210. Min Act: -0.0001

Data Index: 296709 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8661. Min Act: -0.0001

Data Index: 1507200 (Python Code)

Max Activating Token Index: 179

Text #11

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7830. Min Act: -0.0001

Data Index: 1614510 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8555. Min Act: -0.0001

Data Index: 1433422 (Python Code)

Max Activating Token Index: 214

Text #13

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.9361. Min Act: -0.0001

Data Index: 1360388 (Python Code)

Max Activating Token Index: 436

Text #14

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7705. Min Act: -0.0001

Data Index: 1568606 (Python Code)

Max Activating Token Index: 203

Text #15

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8477. Min Act: -0.0001

Data Index: 1424917 (Python Code)

Max Activating Token Index: 1010

Text #16

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7263. Min Act: -0.0001

Data Index: 1367432 (Python Code)

Max Activating Token Index: 553

Text #17

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8956. Min Act: -0.0001

Data Index: 1588538 (Python Code)

Max Activating Token Index: 860

Text #18

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.7940. Min Act: -0.0001

Data Index: 1455978 (Python Code)

Max Activating Token Index: 926

Text #19

Max Range: 1.0030. Min Range: -1.0030

Max Act: 0.8224. Min Act: -0.0001

Data Index: 1436697 (Python Code)

Max Activating Token Index: 50