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

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

Neuron 1794 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.8650. Min Act: -0.0000

Data Index: 655919 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.6879. Min Act: -0.0000

Data Index: 57156 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.6725. Min Act: -0.0000

Data Index: 1107969 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.9840. Min Act: -0.0000

Data Index: 727840 (C4 (Web Text))

Max Activating Token Index: 257

Text #4

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.8106. Min Act: -0.0000

Data Index: 784252 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.8157. Min Act: -0.0000

Data Index: 1140122 (C4 (Web Text))

Max Activating Token Index: 264

Text #6

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.7807. Min Act: -0.0000

Data Index: 305244 (C4 (Web Text))

Max Activating Token Index: 590

Text #7

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.7662. Min Act: -0.0000

Data Index: 496503 (C4 (Web Text))

Max Activating Token Index: 203

Text #8

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.6045. Min Act: -0.0000

Data Index: 462127 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.5711. Min Act: -0.0000

Data Index: 205225 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.6218. Min Act: -0.0000

Data Index: 25484 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.5648. Min Act: -0.0000

Data Index: 753701 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.3932. Min Act: -0.0000

Data Index: 111270 (C4 (Web Text))

Max Activating Token Index: 779

Text #13

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.4773. Min Act: -0.0000

Data Index: 1067418 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.4301. Min Act: -0.0000

Data Index: 805811 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.3095. Min Act: -0.0000

Data Index: 1125921 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.4180. Min Act: -0.0000

Data Index: 872734 (C4 (Web Text))

Max Activating Token Index: 538

Text #17

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.3412. Min Act: -0.0000

Data Index: 140303 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.3555. Min Act: -0.0000

Data Index: 733820 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 2.9840. Min Range: -2.9840

Max Act: 2.3511. Min Act: -0.0000

Data Index: 288176 (C4 (Web Text))

Max Activating Token Index: 636