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

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

Neuron 4161 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: 1.0456. Min Range: -1.0456

Max Act: 1.0456. Min Act: -0.0000

Data Index: 1091973 (C4 (Web Text))

Max Activating Token Index: 946

Text #1

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.9838. Min Act: -0.0000

Data Index: 1131288 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.9069. Min Act: -0.0000

Data Index: 242508 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.8363. Min Act: -0.0000

Data Index: 674445 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.8658. Min Act: -0.0000

Data Index: 601415 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.8539. Min Act: -0.0000

Data Index: 659613 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7880. Min Act: -0.0000

Data Index: 481427 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7852. Min Act: -0.0000

Data Index: 471780 (C4 (Web Text))

Max Activating Token Index: 486

Text #8

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.8023. Min Act: -0.0000

Data Index: 308804 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1404490 (Python Code)

Max Activating Token Index: 287

Text #10

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7669. Min Act: -0.0000

Data Index: 65244 (C4 (Web Text))

Max Activating Token Index: 336

Text #11

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7127. Min Act: -0.0000

Data Index: 867161 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7470. Min Act: -0.0000

Data Index: 77931 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7469. Min Act: -0.0000

Data Index: 1120326 (C4 (Web Text))

Max Activating Token Index: 726

Text #14

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7176. Min Act: -0.0000

Data Index: 211836 (C4 (Web Text))

Max Activating Token Index: 466

Text #15

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1223249 (C4 (Web Text))

Max Activating Token Index: 518

Text #16

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7176. Min Act: -0.0000

Data Index: 79273 (C4 (Web Text))

Max Activating Token Index: 453

Text #17

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7564. Min Act: -0.0000

Data Index: 484202 (C4 (Web Text))

Max Activating Token Index: 559

Text #18

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.7036. Min Act: -0.0000

Data Index: 1175242 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 1.0456. Min Range: -1.0456

Max Act: 0.6768. Min Act: -0.0000

Data Index: 447485 (C4 (Web Text))

Max Activating Token Index: 299