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

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

Neuron 2228 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.3743. Min Act: -0.0000

Data Index: 498934 (C4 (Web Text))

Max Activating Token Index: 6

Text #1

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.3930. Min Act: -0.0000

Data Index: 836955 (C4 (Web Text))

Max Activating Token Index: 631

Text #2

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.9377. Min Act: -0.0000

Data Index: 1006787 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 2.3930. Min Range: -2.3930

Max Act: 2.0531. Min Act: -0.0000

Data Index: 266903 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.9950. Min Act: -0.0000

Data Index: 737741 (C4 (Web Text))

Max Activating Token Index: 616

Text #5

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.8795. Min Act: -0.0000

Data Index: 518717 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.7400. Min Act: -0.0000

Data Index: 998622 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.7899. Min Act: -0.0000

Data Index: 398690 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.7730. Min Act: -0.0000

Data Index: 930030 (C4 (Web Text))

Max Activating Token Index: 236

Text #9

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.7244. Min Act: -0.0000

Data Index: 1186765 (C4 (Web Text))

Max Activating Token Index: 913

Text #10

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.7048. Min Act: -0.0000

Data Index: 837297 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.6460. Min Act: -0.0000

Data Index: 256209 (C4 (Web Text))

Max Activating Token Index: 314

Text #12

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.5106. Min Act: -0.0000

Data Index: 1037001 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.5946. Min Act: -0.0000

Data Index: 262298 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1257046 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.5747. Min Act: -0.0000

Data Index: 896139 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.5838. Min Act: -0.0000

Data Index: 478832 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.5650. Min Act: -0.0000

Data Index: 1145871 (C4 (Web Text))

Max Activating Token Index: 87

Text #18

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.4518. Min Act: -0.0000

Data Index: 462508 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 2.3930. Min Range: -2.3930

Max Act: 1.5285. Min Act: -0.0000

Data Index: 938355 (C4 (Web Text))

Max Activating Token Index: 537