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

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

Neuron 2591 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: 0.7522. Min Range: -0.7522

Max Act: 0.7522. Min Act: -0.0000

Data Index: 69032 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6672. Min Act: -0.0000

Data Index: 416640 (C4 (Web Text))

Max Activating Token Index: 546

Text #2

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1297198 (C4 (Web Text))

Max Activating Token Index: 518

Text #3

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6666. Min Act: -0.0000

Data Index: 195215 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6626. Min Act: -0.0000

Data Index: 879824 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6724. Min Act: -0.0000

Data Index: 113351 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6468. Min Act: -0.0000

Data Index: 991850 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6875. Min Act: -0.0000

Data Index: 299481 (C4 (Web Text))

Max Activating Token Index: 480

Text #8

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6593. Min Act: -0.0000

Data Index: 110291 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6091. Min Act: -0.0000

Data Index: 800749 (C4 (Web Text))

Max Activating Token Index: 432

Text #10

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6909. Min Act: -0.0000

Data Index: 773201 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6459. Min Act: -0.0000

Data Index: 219065 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6260. Min Act: -0.0000

Data Index: 529616 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6206. Min Act: -0.0000

Data Index: 745642 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6235. Min Act: -0.0000

Data Index: 594590 (C4 (Web Text))

Max Activating Token Index: 512

Text #15

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6404. Min Act: -0.0000

Data Index: 142539 (C4 (Web Text))

Max Activating Token Index: 570

Text #16

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6211. Min Act: -0.0000

Data Index: 832869 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1204872 (C4 (Web Text))

Max Activating Token Index: 626

Text #18

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.6343. Min Act: -0.0000

Data Index: 817247 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.7522. Min Range: -0.7522

Max Act: 0.5977. Min Act: -0.0000

Data Index: 910785 (C4 (Web Text))

Max Activating Token Index: 324