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

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

Neuron 4433 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.2206. Min Act: -0.0000

Data Index: 681952 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0968. Min Act: -0.0000

Data Index: 54962 (C4 (Web Text))

Max Activating Token Index: 127

Text #2

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.1420. Min Act: -0.0000

Data Index: 126288 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.1236. Min Act: -0.0000

Data Index: 702185 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0177. Min Act: -0.0000

Data Index: 840676 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0766. Min Act: -0.0000

Data Index: 62083 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.1125. Min Act: -0.0000

Data Index: 171132 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0879. Min Act: -0.0000

Data Index: 194311 (C4 (Web Text))

Max Activating Token Index: 417

Text #8

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0261. Min Act: -0.0000

Data Index: 1184536 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9907. Min Act: -0.0000

Data Index: 970077 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0079. Min Act: -0.0000

Data Index: 903468 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0468. Min Act: -0.0000

Data Index: 294656 (C4 (Web Text))

Max Activating Token Index: 751

Text #12

Max Range: 1.2206. Min Range: -1.2206

Max Act: 1.0068. Min Act: -0.0000

Data Index: 682857 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9976. Min Act: -0.0000

Data Index: 865463 (C4 (Web Text))

Max Activating Token Index: 221

Text #14

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9918. Min Act: -0.0000

Data Index: 104872 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9869. Min Act: -0.0000

Data Index: 419150 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9360. Min Act: -0.0000

Data Index: 932677 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1102464 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9317. Min Act: -0.0000

Data Index: 526327 (C4 (Web Text))

Max Activating Token Index: 279

Text #19

Max Range: 1.2206. Min Range: -1.2206

Max Act: 0.9643. Min Act: -0.0000

Data Index: 311470 (C4 (Web Text))

Max Activating Token Index: 494