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

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

Neuron 5402 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.6012. Min Act: -0.0002

Data Index: 351820 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.6113. Min Act: -0.0002

Data Index: 682775 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4779. Min Act: -0.0002

Data Index: 1099715 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.5339. Min Act: -0.0002

Data Index: 1008093 (C4 (Web Text))

Max Activating Token Index: 577

Text #4

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4661. Min Act: -0.0002

Data Index: 653782 (C4 (Web Text))

Max Activating Token Index: 697

Text #5

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.5173. Min Act: -0.0002

Data Index: 204051 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4718. Min Act: -0.0002

Data Index: 21966 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.5103. Min Act: -0.0002

Data Index: 374926 (C4 (Web Text))

Max Activating Token Index: 556

Text #8

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4514. Min Act: -0.0002

Data Index: 1231107 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4829. Min Act: -0.0002

Data Index: 458246 (C4 (Web Text))

Max Activating Token Index: 545

Text #10

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4150. Min Act: -0.0002

Data Index: 248098 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4107. Min Act: -0.0002

Data Index: 913576 (C4 (Web Text))

Max Activating Token Index: 402

Text #12

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4068. Min Act: -0.0002

Data Index: 50121 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4237. Min Act: -0.0002

Data Index: 844338 (C4 (Web Text))

Max Activating Token Index: 346

Text #14

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4188. Min Act: -0.0002

Data Index: 149435 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4198. Min Act: -0.0002

Data Index: 1184865 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4120. Min Act: -0.0002

Data Index: 1173102 (C4 (Web Text))

Max Activating Token Index: 149

Text #17

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4098. Min Act: -0.0002

Data Index: 731541 (C4 (Web Text))

Max Activating Token Index: 323

Text #18

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.4207. Min Act: -0.0002

Data Index: 372502 (C4 (Web Text))

Max Activating Token Index: 129

Text #19

Max Range: 1.6113. Min Range: -1.6113

Max Act: 1.3999. Min Act: -0.0002

Data Index: 579949 (C4 (Web Text))

Max Activating Token Index: 832