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

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

Neuron 3918 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: 0.5891. Min Range: -0.5891

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1029326 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5793. Min Act: -0.0000

Data Index: 1144465 (C4 (Web Text))

Max Activating Token Index: 757

Text #2

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5120. Min Act: -0.0000

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5137. Min Act: -0.0000

Data Index: 348143 (C4 (Web Text))

Max Activating Token Index: 539

Text #4

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5159. Min Act: -0.0000

Data Index: 899914 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5270. Min Act: -0.0000

Data Index: 127912 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4846. Min Act: -0.0000

Data Index: 299040 (C4 (Web Text))

Max Activating Token Index: 600

Text #7

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5092. Min Act: -0.0000

Data Index: 486311 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4701. Min Act: -0.0000

Data Index: 1317481 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4670. Min Act: -0.0000

Data Index: 974379 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4754. Min Act: -0.0000

Data Index: 1108500 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4461. Min Act: -0.0000

Data Index: 291401 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4346. Min Act: -0.0000

Data Index: 178548 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4406. Min Act: -0.0000

Data Index: 26687 (C4 (Web Text))

Max Activating Token Index: 139

Text #14

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4349. Min Act: -0.0000

Data Index: 1257144 (C4 (Web Text))

Max Activating Token Index: 496

Text #15

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4338. Min Act: -0.0000

Data Index: 553857 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4163. Min Act: -0.0000

Data Index: 296254 (C4 (Web Text))

Max Activating Token Index: 101

Text #17

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4001. Min Act: -0.0000

Data Index: 609369 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.3976. Min Act: -0.0000

Data Index: 621164 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4105. Min Act: 0.0000

Data Index: 1147258 (C4 (Web Text))

Max Activating Token Index: 260