Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 774 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0006

Data Index: 801596 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0006

Data Index: 664869 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0037. Min Act: -0.0006

Data Index: 899763 (C4 (Web Text))

Max Activating Token Index: 99

Text #3

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0006

Data Index: 987272 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0037. Min Act: -0.0006

Data Index: 449388 (C4 (Web Text))

Max Activating Token Index: 51

Text #5

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0006

Data Index: 356961 (C4 (Web Text))

Max Activating Token Index: 382

Text #6

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0006

Data Index: 624940 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0006

Data Index: 959100 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0036. Min Act: -0.0006

Data Index: 873165 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0006

Data Index: 581904 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0006

Data Index: 859762 (C4 (Web Text))

Max Activating Token Index: 715

Text #11

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0006

Data Index: 1110590 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0006

Data Index: 573556 (C4 (Web Text))

Max Activating Token Index: 231

Text #13

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0006

Data Index: 980875 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0006

Data Index: 144756 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0006

Data Index: 386651 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1258545 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0006

Data Index: 819628 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0033. Min Act: -0.0006

Data Index: 745788 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0034. Min Act: -0.0006

Data Index: 1018715 (C4 (Web Text))

Max Activating Token Index: 53