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

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

Neuron 582 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.2436. Min Act: -0.0001

Data Index: 710837 (C4 (Web Text))

Max Activating Token Index: 195

Text #1

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.2706. Min Act: -0.0001

Data Index: 355524 (C4 (Web Text))

Max Activating Token Index: 509

Text #2

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.1799. Min Act: -0.0001

Data Index: 234025 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0562. Min Act: -0.0001

Data Index: 691256 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.1603. Min Act: -0.0001

Data Index: 1128483 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0981. Min Act: -0.0001

Data Index: 1085707 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0733. Min Act: -0.0001

Data Index: 182600 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0245. Min Act: -0.0001

Data Index: 974904 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0005. Min Act: -0.0001

Data Index: 308192 (C4 (Web Text))

Max Activating Token Index: 338

Text #9

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0906. Min Act: -0.0001

Data Index: 599328 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0293. Min Act: -0.0001

Data Index: 871438 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0780. Min Act: -0.0001

Data Index: 355327 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0739. Min Act: -0.0001

Data Index: 552381 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0202. Min Act: -0.0001

Data Index: 495782 (C4 (Web Text))

Max Activating Token Index: 101

Text #14

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0325. Min Act: -0.0001

Data Index: 341239 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.1572. Min Act: -0.0001

Data Index: 436018 (C4 (Web Text))

Max Activating Token Index: 462

Text #16

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0594. Min Act: -0.0001

Data Index: 79149 (C4 (Web Text))

Max Activating Token Index: 531

Text #17

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0250. Min Act: -0.0001

Data Index: 1256841 (C4 (Web Text))

Max Activating Token Index: 436

Text #18

Max Range: 1.2706. Min Range: -1.2706

Max Act: 1.0653. Min Act: -0.0001

Data Index: 56173 (C4 (Web Text))

Max Activating Token Index: 385

Text #19

Max Range: 1.2706. Min Range: -1.2706

Max Act: 0.9988. Min Act: -0.0001

Data Index: 816253 (C4 (Web Text))

Max Activating Token Index: 467