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

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

Neuron 518 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: 0.1292. Min Range: -0.1292

Max Act: 0.1292. Min Act: -0.0005

Data Index: 1203495 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1075. Min Act: -0.0005

Data Index: 309966 (C4 (Web Text))

Max Activating Token Index: 652

Text #2

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1188. Min Act: -0.0005

Data Index: 243203 (C4 (Web Text))

Max Activating Token Index: 821

Text #3

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1107. Min Act: -0.0005

Data Index: 794408 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1102. Min Act: -0.0005

Data Index: 1103805 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1130. Min Act: -0.0005

Data Index: 686235 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1095. Min Act: -0.0005

Data Index: 717266 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1080. Min Act: -0.0005

Data Index: 1094556 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1077. Min Act: -0.0005

Data Index: 125396 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1020. Min Act: -0.0005

Data Index: 358601 (C4 (Web Text))

Max Activating Token Index: 557

Text #10

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1058. Min Act: -0.0005

Data Index: 189820 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0943. Min Act: -0.0005

Data Index: 1165956 (C4 (Web Text))

Max Activating Token Index: 688

Text #12

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0970. Min Act: -0.0005

Data Index: 332644 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1001. Min Act: -0.0005

Data Index: 1207785 (C4 (Web Text))

Max Activating Token Index: 288

Text #14

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0965. Min Act: -0.0005

Data Index: 1207471 (C4 (Web Text))

Max Activating Token Index: 940

Text #15

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1039. Min Act: -0.0005

Data Index: 729865 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.0947. Min Act: -0.0005

Data Index: 1300927 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1023. Min Act: -0.0005

Data Index: 683012 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1056. Min Act: -0.0005

Data Index: 1079247 (C4 (Web Text))

Max Activating Token Index: 1017

Text #19

Max Range: 0.1292. Min Range: -0.1292

Max Act: 0.1015. Min Act: -0.0005

Data Index: 165053 (C4 (Web Text))

Max Activating Token Index: 596