Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3648 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0735. Min Act: -0.0001

Data Index: 951244 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 1.0775. Min Range: -1.0775

Max Act: 1.0775. Min Act: -0.0001

Data Index: 84850 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.9873. Min Act: -0.0001

Data Index: 701836 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8865. Min Act: -0.0001

Data Index: 885573 (C4 (Web Text))

Max Activating Token Index: 227

Text #4

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8698. Min Act: -0.0001

Data Index: 506861 (C4 (Web Text))

Max Activating Token Index: 958

Text #5

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8437. Min Act: -0.0001

Data Index: 626494 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8442. Min Act: -0.0001

Data Index: 1010044 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7211. Min Act: -0.0001

Data Index: 568176 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8061. Min Act: -0.0001

Data Index: 846102 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7939. Min Act: -0.0001

Data Index: 1333848 (C4 (Web Text))

Max Activating Token Index: 344

Text #10

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7530. Min Act: -0.0001

Data Index: 355183 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7528. Min Act: -0.0001

Data Index: 773571 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7481. Min Act: -0.0001

Data Index: 883586 (C4 (Web Text))

Max Activating Token Index: 428

Text #13

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7236. Min Act: -0.0001

Data Index: 884976 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7206. Min Act: -0.0001

Data Index: 681669 (C4 (Web Text))

Max Activating Token Index: 992

Text #15

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8115. Min Act: -0.0001

Data Index: 1199399 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.8100. Min Act: -0.0001

Data Index: 1031218 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7084. Min Act: -0.0001

Data Index: 433915 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7577. Min Act: -0.0001

Data Index: 616792 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 1.0775. Min Range: -1.0775

Max Act: 0.7020. Min Act: -0.0001

Data Index: 729198 (C4 (Web Text))

Max Activating Token Index: 769