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

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

Neuron 5855 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: 1.2776. Min Range: -1.2776

Max Act: 1.0870. Min Act: -0.0001

Data Index: 423459 (C4 (Web Text))

Max Activating Token Index: 174

Text #1

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.1230. Min Act: -0.0001

Data Index: 665928 (C4 (Web Text))

Max Activating Token Index: 256

Text #2

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.2776. Min Act: -0.0001

Data Index: 1354944 (C4 (Web Text))

Max Activating Token Index: 249

Text #3

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.2196. Min Act: -0.0001

Data Index: 652681 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.1216. Min Act: -0.0001

Data Index: 1272819 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.0220. Min Act: -0.0001

Data Index: 572952 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.9827. Min Act: -0.0001

Data Index: 280234 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.1027. Min Act: -0.0001

Data Index: 455604 (C4 (Web Text))

Max Activating Token Index: 101

Text #8

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.0061. Min Act: -0.0001

Data Index: 1278221 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.0036. Min Act: -0.0001

Data Index: 1216385 (C4 (Web Text))

Max Activating Token Index: 538

Text #10

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.0622. Min Act: -0.0001

Data Index: 781320 (C4 (Web Text))

Max Activating Token Index: 474

Text #11

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.9310. Min Act: -0.0001

Data Index: 551983 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.2776. Min Range: -1.2776

Max Act: 1.1391. Min Act: -0.0001

Data Index: 1344797 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.9744. Min Act: -0.0001

Data Index: 837423 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.9369. Min Act: -0.0001

Data Index: 406629 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.9344. Min Act: -0.0001

Data Index: 879408 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.8825. Min Act: -0.0001

Data Index: 662924 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.9650. Min Act: -0.0001

Data Index: 136686 (C4 (Web Text))

Max Activating Token Index: 83

Text #18

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.7499. Min Act: -0.0001

Data Index: 1165766 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 1.2776. Min Range: -1.2776

Max Act: 0.8765. Min Act: -0.0001

Data Index: 466509 (C4 (Web Text))

Max Activating Token Index: 625