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

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

Neuron 1642 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0001

Data Index: 735153 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1242. Min Act: -0.0000

Data Index: 1225619 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1151. Min Act: -0.0001

Data Index: 170566 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1145. Min Act: -0.0000

Data Index: 49654 (C4 (Web Text))

Max Activating Token Index: 841

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1142. Min Act: -0.0001

Data Index: 206912 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1115. Min Act: -0.0001

Data Index: 31809 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1040. Min Act: -0.0000

Data Index: 310141 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1081. Min Act: -0.0000

Data Index: 1190126 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1037. Min Act: -0.0000

Data Index: 690743 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1074. Min Act: -0.0000

Data Index: 662618 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1073. Min Act: -0.0000

Data Index: 968023 (C4 (Web Text))

Max Activating Token Index: 233

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1054. Min Act: -0.0001

Data Index: 17129 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1052. Min Act: -0.0000

Data Index: 425397 (C4 (Web Text))

Max Activating Token Index: 579

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1071. Min Act: -0.0001

Data Index: 463889 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1065. Min Act: -0.0000

Data Index: 249992 (C4 (Web Text))

Max Activating Token Index: 195

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1013385 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1022. Min Act: -0.0000

Data Index: 1209827 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1014. Min Act: -0.0000

Data Index: 48028 (C4 (Web Text))

Max Activating Token Index: 184

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1091487 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1196509 (C4 (Web Text))

Max Activating Token Index: 772