Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4275 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.8284. Min Act: -0.0000

Data Index: 274347 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1052737 (C4 (Web Text))

Max Activating Token Index: 393

Text #2

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6713. Min Act: -0.0000

Data Index: 314285 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6656. Min Act: -0.0000

Data Index: 802663 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6501. Min Act: -0.0000

Data Index: 678895 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5849. Min Act: -0.0000

Data Index: 24053 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.6089. Min Act: -0.0000

Data Index: 68359 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5755. Min Act: -0.0000

Data Index: 529549 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5283. Min Act: -0.0000

Data Index: 606224 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5400. Min Act: -0.0000

Data Index: 230232 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1007312 (C4 (Web Text))

Max Activating Token Index: 114

Text #11

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5305. Min Act: -0.0000

Data Index: 949122 (C4 (Web Text))

Max Activating Token Index: 589

Text #12

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5435. Min Act: -0.0000

Data Index: 578250 (C4 (Web Text))

Max Activating Token Index: 273

Text #13

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5058. Min Act: -0.0000

Data Index: 427628 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5413. Min Act: -0.0000

Data Index: 1044774 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.4805. Min Act: -0.0000

Data Index: 73989 (C4 (Web Text))

Max Activating Token Index: 739

Text #16

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1189451 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.5058. Min Act: -0.0000

Data Index: 721380 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.4959. Min Act: -0.0000

Data Index: 604514 (C4 (Web Text))

Max Activating Token Index: 538

Text #19

Max Range: 0.8284. Min Range: -0.8284

Max Act: 0.4953. Min Act: -0.0000

Data Index: 592768 (C4 (Web Text))

Max Activating Token Index: 324