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

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

Neuron 544 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: 0.6287. Min Range: -0.6287

Max Act: 0.6287. Min Act: -0.0000

Data Index: 613796 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.6012. Min Act: -0.0000

Data Index: 333559 (C4 (Web Text))

Max Activating Token Index: 729

Text #2

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.5323. Min Act: -0.0000

Data Index: 883658 (C4 (Web Text))

Max Activating Token Index: 198

Text #3

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.5495. Min Act: -0.0000

Data Index: 1220475 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1248962 (C4 (Web Text))

Max Activating Token Index: 693

Text #5

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4659. Min Act: -0.0000

Data Index: 767887 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4637. Min Act: -0.0000

Data Index: 879926 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4429. Min Act: -0.0000

Data Index: 785780 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4604. Min Act: -0.0000

Data Index: 517711 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4119. Min Act: -0.0000

Data Index: 1000931 (C4 (Web Text))

Max Activating Token Index: 470

Text #10

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4106. Min Act: -0.0000

Data Index: 501480 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4335. Min Act: -0.0000

Data Index: 407145 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4147. Min Act: -0.0000

Data Index: 366425 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4079. Min Act: -0.0000

Data Index: 1015418 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4132. Min Act: -0.0000

Data Index: 976352 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4097. Min Act: -0.0000

Data Index: 1338719 (C4 (Web Text))

Max Activating Token Index: 536

Text #16

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1039919 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.4002. Min Act: -0.0000

Data Index: 1243488 (C4 (Web Text))

Max Activating Token Index: 467

Text #18

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.3717. Min Act: -0.0000

Data Index: 414054 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.6287. Min Range: -0.6287

Max Act: 0.3796. Min Act: -0.0000

Data Index: 122985 (C4 (Web Text))

Max Activating Token Index: 486