Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1593 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.4335. Min Act: -0.0001

Data Index: 1566776 (Python Code)

Max Activating Token Index: 71

Text #1

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.4389. Min Act: -0.0001

Data Index: 1380893 (Python Code)

Max Activating Token Index: 973

Text #2

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.5047. Min Act: -0.0001

Data Index: 1649646 (Python Code)

Max Activating Token Index: 195

Text #3

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.4374. Min Act: -0.0001

Data Index: 1379538 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.4305. Min Act: -0.0001

Data Index: 1429361 (Python Code)

Max Activating Token Index: 575

Text #5

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3210. Min Act: -0.0001

Data Index: 1438717 (Python Code)

Max Activating Token Index: 178

Text #6

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3903. Min Act: -0.0001

Data Index: 1387095 (Python Code)

Max Activating Token Index: 468

Text #7

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3718. Min Act: -0.0001

Data Index: 1565423 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.1816. Min Act: -0.0001

Data Index: 1495473 (Python Code)

Max Activating Token Index: 326

Text #9

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.2986. Min Act: -0.0001

Data Index: 1589837 (Python Code)

Max Activating Token Index: 169

Text #10

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.2568. Min Act: -0.0001

Data Index: 1494222 (Python Code)

Max Activating Token Index: 205

Text #11

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3087. Min Act: -0.0001

Data Index: 1435174 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3136. Min Act: -0.0001

Data Index: 1628556 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.1754. Min Act: -0.0001

Data Index: 1517592 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3300. Min Act: -0.0001

Data Index: 1463408 (Python Code)

Max Activating Token Index: 810

Text #15

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.1814. Min Act: -0.0001

Data Index: 1360761 (Python Code)

Max Activating Token Index: 80

Text #16

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.2827. Min Act: -0.0001

Data Index: 1541012 (Python Code)

Max Activating Token Index: 518

Text #17

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3021. Min Act: -0.0001

Data Index: 1561468 (Python Code)

Max Activating Token Index: 221

Text #18

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.2228. Min Act: -0.0001

Data Index: 1529298 (Python Code)

Max Activating Token Index: 783

Text #19

Max Range: 1.5047. Min Range: -1.5047

Max Act: 1.3019. Min Act: -0.0001

Data Index: 1454932 (Python Code)

Max Activating Token Index: 539