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

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

Neuron 3854 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5087. Min Range: -2.5087

Max Act: 2.5087. Min Act: -0.0000

Data Index: 411623 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 2.5087. Min Range: -2.5087

Max Act: 2.2291. Min Act: -0.0000

Data Index: 936265 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 2.5087. Min Range: -2.5087

Max Act: 2.3471. Min Act: -0.0000

Data Index: 141251 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 2.5087. Min Range: -2.5087

Max Act: 2.3274. Min Act: -0.0000

Data Index: 730218 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 2.5087. Min Range: -2.5087

Max Act: 2.1245. Min Act: -0.0000

Data Index: 1346062 (C4 (Web Text))

Max Activating Token Index: 323

Text #5

Max Range: 2.5087. Min Range: -2.5087

Max Act: 2.1385. Min Act: -0.0000

Data Index: 1018326 (C4 (Web Text))

Max Activating Token Index: 246

Text #6

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.9805. Min Act: -0.0000

Data Index: 159891 (C4 (Web Text))

Max Activating Token Index: 220

Text #7

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.9731. Min Act: -0.0000

Data Index: 1038803 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 2.5087. Min Range: -2.5087

Max Act: 2.0711. Min Act: 0.0000

Data Index: 174777 (C4 (Web Text))

Max Activating Token Index: 228

Text #9

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.8069. Min Act: 0.0000

Data Index: 1094739 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.8471. Min Act: 0.0000

Data Index: 1262210 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.9737. Min Act: 0.0000

Data Index: 1024073 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.9793. Min Act: 0.0000

Data Index: 1011351 (C4 (Web Text))

Max Activating Token Index: 966

Text #13

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.7620. Min Act: -0.0000

Data Index: 1230654 (C4 (Web Text))

Max Activating Token Index: 556

Text #14

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.9656. Min Act: -0.0000

Data Index: 715635 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.8043. Min Act: -0.0000

Data Index: 856815 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.8885. Min Act: -0.0000

Data Index: 830332 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.7118. Min Act: -0.0000

Data Index: 466650 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.6919. Min Act: 0.0000

Data Index: 505517 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 2.5087. Min Range: -2.5087

Max Act: 1.7182. Min Act: -0.0000

Data Index: 608940 (C4 (Web Text))

Max Activating Token Index: 198