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

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

Neuron 320 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0001

Data Index: 551444 (C4 (Web Text))

Max Activating Token Index: 565

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0150. Min Act: -0.0001

Data Index: 57817 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0128. Min Act: -0.0001

Data Index: 879207 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0113. Min Act: -0.0001

Data Index: 1025555 (C4 (Web Text))

Max Activating Token Index: 507

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0118. Min Act: -0.0001

Data Index: 963882 (C4 (Web Text))

Max Activating Token Index: 686

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0126. Min Act: -0.0001

Data Index: 1022811 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0108. Min Act: -0.0001

Data Index: 953341 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0116. Min Act: -0.0001

Data Index: 1018048 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0111. Min Act: -0.0001

Data Index: 801725 (C4 (Web Text))

Max Activating Token Index: 168

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0106. Min Act: -0.0001

Data Index: 1077764 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0109. Min Act: -0.0001

Data Index: 1247565 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0111. Min Act: -0.0001

Data Index: 33597 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0104. Min Act: -0.0001

Data Index: 279089 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0095. Min Act: -0.0001

Data Index: 877390 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0118. Min Act: -0.0001

Data Index: 532245 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0112. Min Act: -0.0001

Data Index: 701865 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0118. Min Act: -0.0001

Data Index: 834412 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0102. Min Act: -0.0001

Data Index: 1028654 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0089. Min Act: -0.0001

Data Index: 771916 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0109. Min Act: -0.0001

Data Index: 307581 (C4 (Web Text))

Max Activating Token Index: 121