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

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

Neuron 977 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1044. Min Act: -0.0000

Data Index: 1313806 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1077. Min Act: -0.0002

Data Index: 18531 (C4 (Web Text))

Max Activating Token Index: 13

Text #2

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1063. Min Act: -0.0001

Data Index: 553065 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1098. Min Act: -0.0002

Data Index: 29456 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1093. Min Act: -0.0002

Data Index: 254516 (C4 (Web Text))

Max Activating Token Index: 863

Text #5

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1125917 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1070. Min Act: -0.0002

Data Index: 106143 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.1026. Min Act: -0.0001

Data Index: 358164 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0966. Min Act: -0.0002

Data Index: 346402 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0999. Min Act: -0.0002

Data Index: 137681 (C4 (Web Text))

Max Activating Token Index: 695

Text #10

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0956. Min Act: -0.0001

Data Index: 1239817 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0952. Min Act: -0.0001

Data Index: 1222173 (C4 (Web Text))

Max Activating Token Index: 557

Text #12

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0939. Min Act: -0.0001

Data Index: 656767 (C4 (Web Text))

Max Activating Token Index: 272

Text #13

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0940. Min Act: -0.0001

Data Index: 642265 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0968. Min Act: -0.0002

Data Index: 593966 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0995. Min Act: -0.0002

Data Index: 728721 (C4 (Web Text))

Max Activating Token Index: 682

Text #16

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0933. Min Act: -0.0001

Data Index: 971421 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0931. Min Act: -0.0001

Data Index: 578449 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0939. Min Act: -0.0000

Data Index: 980651 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 0.1098. Min Range: -0.1098

Max Act: 0.0925. Min Act: -0.0001

Data Index: 392255 (C4 (Web Text))

Max Activating Token Index: 608