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

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

Neuron 2773 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.4031. Min Act: -0.0002

Data Index: 1472421 (Python Code)

Max Activating Token Index: 599

Text #1

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2485. Min Act: -0.0002

Data Index: 767041 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.3352. Min Act: -0.0002

Data Index: 1281791 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2569. Min Act: -0.0002

Data Index: 1495637 (Python Code)

Max Activating Token Index: 598

Text #4

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.3262. Min Act: -0.0002

Data Index: 1360525 (Python Code)

Max Activating Token Index: 932

Text #5

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.3864. Min Act: -0.0002

Data Index: 1449034 (Python Code)

Max Activating Token Index: 243

Text #6

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.3385. Min Act: -0.0002

Data Index: 1228873 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.3317. Min Act: -0.0002

Data Index: 1590933 (Python Code)

Max Activating Token Index: 558

Text #8

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1725. Min Act: -0.0002

Data Index: 947359 (C4 (Web Text))

Max Activating Token Index: 608

Text #9

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2525. Min Act: -0.0002

Data Index: 1267081 (C4 (Web Text))

Max Activating Token Index: 230

Text #10

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2106. Min Act: -0.0002

Data Index: 283112 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1206. Min Act: -0.0002

Data Index: 926730 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2378. Min Act: -0.0002

Data Index: 1306067 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2950. Min Act: -0.0002

Data Index: 1644158 (Python Code)

Max Activating Token Index: 291

Text #14

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2192. Min Act: -0.0002

Data Index: 1527981 (Python Code)

Max Activating Token Index: 93

Text #15

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.2155. Min Act: -0.0002

Data Index: 1599504 (Python Code)

Max Activating Token Index: 402

Text #16

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1412. Min Act: -0.0002

Data Index: 1474192 (Python Code)

Max Activating Token Index: 82

Text #17

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.1672. Min Act: -0.0002

Data Index: 753305 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.4031. Min Range: -1.4031

Max Act: 0.9093. Min Act: -0.0002

Data Index: 1477036 (Python Code)

Max Activating Token Index: 629

Text #19

Max Range: 1.4031. Min Range: -1.4031

Max Act: 1.0841. Min Act: -0.0002

Data Index: 1542371 (Python Code)

Max Activating Token Index: 549