Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 446 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1049. Min Act: -0.0005

Data Index: 1647475 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1164. Min Act: -0.0005

Data Index: 1605968 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1016. Min Act: -0.0005

Data Index: 1519414 (Python Code)

Max Activating Token Index: 823

Text #3

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.1065. Min Act: -0.0005

Data Index: 691393 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0932. Min Act: -0.0005

Data Index: 1552195 (Python Code)

Max Activating Token Index: 330

Text #5

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0919. Min Act: -0.0005

Data Index: 1521161 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0960. Min Act: -0.0005

Data Index: 1369988 (Python Code)

Max Activating Token Index: 437

Text #7

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0899. Min Act: -0.0005

Data Index: 1488040 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0916. Min Act: -0.0005

Data Index: 1380578 (Python Code)

Max Activating Token Index: 289

Text #9

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0911. Min Act: -0.0005

Data Index: 1594533 (Python Code)

Max Activating Token Index: 185

Text #10

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0946. Min Act: -0.0005

Data Index: 1501720 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0897. Min Act: -0.0005

Data Index: 1497071 (Python Code)

Max Activating Token Index: 841

Text #12

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0930. Min Act: -0.0005

Data Index: 1476817 (Python Code)

Max Activating Token Index: 837

Text #13

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0894. Min Act: -0.0005

Data Index: 1444709 (Python Code)

Max Activating Token Index: 661

Text #14

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0862. Min Act: -0.0005

Data Index: 1606456 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0936. Min Act: -0.0005

Data Index: 1535910 (Python Code)

Max Activating Token Index: 861

Text #16

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0924. Min Act: -0.0005

Data Index: 633448 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0878. Min Act: -0.0005

Data Index: 1404924 (Python Code)

Max Activating Token Index: 693

Text #18

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0790. Min Act: -0.0005

Data Index: 1433338 (Python Code)

Max Activating Token Index: 404

Text #19

Max Range: 0.1164. Min Range: -0.1164

Max Act: 0.0852. Min Act: -0.0005

Data Index: 1413729 (Python Code)

Max Activating Token Index: 884