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

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

Neuron 3150 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.4016. Min Act: -0.0000

Data Index: 798183 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.2908. Min Act: -0.0000

Data Index: 384112 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1843. Min Act: -0.0000

Data Index: 743412 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1265692 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1509. Min Act: -0.0000

Data Index: 479061 (C4 (Web Text))

Max Activating Token Index: 781

Text #5

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1022514 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1606. Min Act: -0.0000

Data Index: 960625 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1258. Min Act: -0.0001

Data Index: 401811 (C4 (Web Text))

Max Activating Token Index: 434

Text #8

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.2018. Min Act: -0.0000

Data Index: 1328158 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1316. Min Act: -0.0000

Data Index: 251923 (C4 (Web Text))

Max Activating Token Index: 354

Text #10

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1269. Min Act: -0.0000

Data Index: 129457 (C4 (Web Text))

Max Activating Token Index: 640

Text #11

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1581. Min Act: -0.0000

Data Index: 619637 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1252. Min Act: -0.0000

Data Index: 988302 (C4 (Web Text))

Max Activating Token Index: 872

Text #13

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1198619 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1815. Min Act: -0.0001

Data Index: 1414718 (Python Code)

Max Activating Token Index: 234

Text #15

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1029. Min Act: -0.0000

Data Index: 217030 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.0991. Min Act: -0.0000

Data Index: 910776 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.0668. Min Act: -0.0000

Data Index: 1276287 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.1602. Min Act: -0.0000

Data Index: 42566 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 1.4016. Min Range: -1.4016

Max Act: 1.0822. Min Act: -0.0000

Data Index: 323217 (C4 (Web Text))

Max Activating Token Index: 739