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

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

Neuron 1513 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.6865. Min Act: -0.0000

Data Index: 389398 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5766. Min Act: -0.0000

Data Index: 486493 (C4 (Web Text))

Max Activating Token Index: 540

Text #2

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.6486. Min Act: -0.0000

Data Index: 404251 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.6618. Min Act: -0.0000

Data Index: 228636 (C4 (Web Text))

Max Activating Token Index: 732

Text #4

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4790. Min Act: -0.0000

Data Index: 637534 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5179. Min Act: -0.0000

Data Index: 376519 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5294. Min Act: -0.0000

Data Index: 613846 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5375. Min Act: -0.0000

Data Index: 1333455 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5333. Min Act: -0.0000

Data Index: 684529 (C4 (Web Text))

Max Activating Token Index: 1015

Text #9

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5617. Min Act: -0.0000

Data Index: 421253 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5045. Min Act: -0.0000

Data Index: 887913 (C4 (Web Text))

Max Activating Token Index: 270

Text #11

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.5283. Min Act: -0.0000

Data Index: 277372 (C4 (Web Text))

Max Activating Token Index: 374

Text #12

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4867. Min Act: -0.0000

Data Index: 1350529 (C4 (Web Text))

Max Activating Token Index: 387

Text #13

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4706. Min Act: -0.0000

Data Index: 992041 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4881. Min Act: -0.0000

Data Index: 883738 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4517. Min Act: -0.0000

Data Index: 684452 (C4 (Web Text))

Max Activating Token Index: 819

Text #16

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4718. Min Act: -0.0000

Data Index: 901204 (C4 (Web Text))

Max Activating Token Index: 221

Text #17

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4843. Min Act: -0.0000

Data Index: 659049 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4885. Min Act: -0.0000

Data Index: 203604 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.6865. Min Range: -0.6865

Max Act: 0.4459. Min Act: -0.0000

Data Index: 1265288 (C4 (Web Text))

Max Activating Token Index: 824