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

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

Neuron 3654 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0003

Data Index: 503275 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0092. Min Act: -0.0002

Data Index: 31105 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0003

Data Index: 336783 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0091. Min Act: -0.0002

Data Index: 1503122 (Python Code)

Max Activating Token Index: 709

Text #4

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0090. Min Act: -0.0003

Data Index: 299125 (C4 (Web Text))

Max Activating Token Index: 742

Text #5

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1594282 (Python Code)

Max Activating Token Index: 726

Text #6

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0086. Min Act: -0.0003

Data Index: 913181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1146922 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0081. Min Act: -0.0003

Data Index: 16813 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0078. Min Act: -0.0003

Data Index: 457144 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0078. Min Act: -0.0003

Data Index: 13274 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0076. Min Act: -0.0003

Data Index: 1026656 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0076. Min Act: -0.0002

Data Index: 1171287 (C4 (Web Text))

Max Activating Token Index: 986

Text #13

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0076. Min Act: -0.0003

Data Index: 466025 (C4 (Web Text))

Max Activating Token Index: 767

Text #14

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0073. Min Act: -0.0002

Data Index: 1068448 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1559620 (Python Code)

Max Activating Token Index: 867

Text #16

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0075. Min Act: -0.0002

Data Index: 1068804 (C4 (Web Text))

Max Activating Token Index: 757

Text #17

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0074. Min Act: -0.0002

Data Index: 689498 (C4 (Web Text))

Max Activating Token Index: 846

Text #18

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0073. Min Act: -0.0002

Data Index: 107462 (C4 (Web Text))

Max Activating Token Index: 724

Text #19

Max Range: 0.0092. Min Range: -0.0092

Max Act: 0.0073. Min Act: -0.0003

Data Index: 840676 (C4 (Web Text))

Max Activating Token Index: 1023