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

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

Neuron 1209 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9728. Min Range: -4.9728

Max Act: 4.9728. Min Act: -0.0000

Data Index: 514283 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 4.9728. Min Range: -4.9728

Max Act: 4.5717. Min Act: -0.0000

Data Index: 617724 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 4.9728. Min Range: -4.9728

Max Act: 4.1969. Min Act: -0.0000

Data Index: 935042 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 4.9728. Min Range: -4.9728

Max Act: 4.1604. Min Act: -0.0000

Data Index: 349673 (C4 (Web Text))

Max Activating Token Index: 794

Text #4

Max Range: 4.9728. Min Range: -4.9728

Max Act: 4.1475. Min Act: -0.0000

Data Index: 455158 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 4.9728. Min Range: -4.9728

Max Act: 4.0471. Min Act: -0.0000

Data Index: 1052782 (C4 (Web Text))

Max Activating Token Index: 659

Text #6

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.9810. Min Act: -0.0000

Data Index: 1105372 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.9559. Min Act: -0.0000

Data Index: 1093682 (C4 (Web Text))

Max Activating Token Index: 246

Text #8

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.9314. Min Act: -0.0000

Data Index: 1039988 (C4 (Web Text))

Max Activating Token Index: 128

Text #9

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.9119. Min Act: -0.0000

Data Index: 166514 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.8517. Min Act: -0.0000

Data Index: 1293163 (C4 (Web Text))

Max Activating Token Index: 187

Text #11

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.6226. Min Act: -0.0000

Data Index: 370407 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.7401. Min Act: -0.0000

Data Index: 760651 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.7220. Min Act: -0.0000

Data Index: 930978 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.7091. Min Act: -0.0000

Data Index: 225068 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.8707. Min Act: -0.0000

Data Index: 584141 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.6927. Min Act: -0.0000

Data Index: 954971 (C4 (Web Text))

Max Activating Token Index: 440

Text #17

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.6680. Min Act: -0.0000

Data Index: 986134 (C4 (Web Text))

Max Activating Token Index: 588

Text #18

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.8136. Min Act: -0.0000

Data Index: 1070006 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 4.9728. Min Range: -4.9728

Max Act: 3.4692. Min Act: -0.0000

Data Index: 53933 (C4 (Web Text))

Max Activating Token Index: 180