Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1003 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.3189. Min Act: -0.0001

Data Index: 222381 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.3203. Min Act: -0.0001

Data Index: 1257990 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1770. Min Act: -0.0001

Data Index: 190923 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2668. Min Act: -0.0001

Data Index: 1004863 (C4 (Web Text))

Max Activating Token Index: 431

Text #4

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2524. Min Act: -0.0001

Data Index: 243275 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.3124. Min Act: -0.0001

Data Index: 46848 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.3028. Min Act: -0.0001

Data Index: 847963 (C4 (Web Text))

Max Activating Token Index: 575

Text #7

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2173. Min Act: -0.0001

Data Index: 1299060 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2877. Min Act: -0.0001

Data Index: 686381 (C4 (Web Text))

Max Activating Token Index: 181

Text #9

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2690. Min Act: -0.0001

Data Index: 150237 (C4 (Web Text))

Max Activating Token Index: 612

Text #10

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1300. Min Act: -0.0001

Data Index: 1319632 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1186. Min Act: -0.0001

Data Index: 511399 (C4 (Web Text))

Max Activating Token Index: 364

Text #12

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2438. Min Act: -0.0001

Data Index: 698769 (C4 (Web Text))

Max Activating Token Index: 467

Text #13

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0891. Min Act: -0.0001

Data Index: 1217650 (C4 (Web Text))

Max Activating Token Index: 571

Text #14

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.2186. Min Act: -0.0001

Data Index: 1344306 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1430. Min Act: -0.0001

Data Index: 1167762 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1846. Min Act: -0.0001

Data Index: 219354 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.0640. Min Act: -0.0001

Data Index: 1251894 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1151. Min Act: -0.0001

Data Index: 125434 (C4 (Web Text))

Max Activating Token Index: 738

Text #19

Max Range: 1.3203. Min Range: -1.3203

Max Act: 1.1192. Min Act: -0.0001

Data Index: 813761 (C4 (Web Text))

Max Activating Token Index: 685