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

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

Neuron 3925 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.2492. Min Act: -0.0000

Data Index: 131065 (C4 (Web Text))

Max Activating Token Index: 392

Text #1

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0668. Min Act: -0.0000

Data Index: 466559 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.1675. Min Act: -0.0000

Data Index: 1315026 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.1226. Min Act: 0.0000

Data Index: 52228 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.2199. Min Act: -0.0000

Data Index: 889427 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.1734. Min Act: -0.0000

Data Index: 527540 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0929. Min Act: -0.0000

Data Index: 1136617 (C4 (Web Text))

Max Activating Token Index: 157

Text #7

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.1569. Min Act: -0.0000

Data Index: 29042 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1172400 (C4 (Web Text))

Max Activating Token Index: 235

Text #9

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0850. Min Act: 0.0000

Data Index: 1332110 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.1294. Min Act: 0.0000

Data Index: 257464 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0814. Min Act: 0.0000

Data Index: 1078859 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1068779 (C4 (Web Text))

Max Activating Token Index: 578

Text #13

Max Range: 1.2492. Min Range: -1.2492

Max Act: 0.9982. Min Act: 0.0000

Data Index: 64910 (C4 (Web Text))

Max Activating Token Index: 575

Text #14

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0234. Min Act: -0.0000

Data Index: 534585 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0795. Min Act: -0.0000

Data Index: 525129 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0401. Min Act: 0.0000

Data Index: 45315 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.2492. Min Range: -1.2492

Max Act: 1.0179. Min Act: -0.0000

Data Index: 748986 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 1.2492. Min Range: -1.2492

Max Act: 0.9794. Min Act: -0.0000

Data Index: 1287860 (C4 (Web Text))

Max Activating Token Index: 132

Text #19

Max Range: 1.2492. Min Range: -1.2492

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1167217 (C4 (Web Text))

Max Activating Token Index: 808