Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3090 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0000

Data Index: 642576 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1115. Min Act: -0.0000

Data Index: 1014224 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1072. Min Act: -0.0000

Data Index: 503474 (C4 (Web Text))

Max Activating Token Index: 412

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1268672 (C4 (Web Text))

Max Activating Token Index: 910

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1076. Min Act: -0.0000

Data Index: 357798 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1061. Min Act: -0.0000

Data Index: 1037597 (C4 (Web Text))

Max Activating Token Index: 639

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1111. Min Act: -0.0000

Data Index: 538398 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1054. Min Act: -0.0000

Data Index: 680602 (C4 (Web Text))

Max Activating Token Index: 295

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1087330 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0990. Min Act: -0.0000

Data Index: 38490 (C4 (Web Text))

Max Activating Token Index: 597

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1100. Min Act: -0.0000

Data Index: 476686 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1134. Min Act: -0.0000

Data Index: 466640 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1005966 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1017. Min Act: -0.0000

Data Index: 641291 (C4 (Web Text))

Max Activating Token Index: 777

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1104. Min Act: -0.0000

Data Index: 36420 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1049. Min Act: 0.0000

Data Index: 12983 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1106. Min Act: -0.0000

Data Index: 306096 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1028. Min Act: -0.0000

Data Index: 264422 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0958. Min Act: -0.0000

Data Index: 712618 (C4 (Web Text))

Max Activating Token Index: 886

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0992. Min Act: 0.0000

Data Index: 40796 (C4 (Web Text))

Max Activating Token Index: 132