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

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

Neuron 4830 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.5195. Min Act: -0.0000

Data Index: 692838 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.5258. Min Act: -0.0000

Data Index: 529332 (C4 (Web Text))

Max Activating Token Index: 577

Text #2

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4754. Min Act: -0.0000

Data Index: 170029 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.5075. Min Act: -0.0000

Data Index: 335524 (C4 (Web Text))

Max Activating Token Index: 340

Text #4

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4694. Min Act: -0.0000

Data Index: 905912 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4806. Min Act: -0.0000

Data Index: 409238 (C4 (Web Text))

Max Activating Token Index: 733

Text #6

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4738. Min Act: -0.0000

Data Index: 752878 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4555. Min Act: -0.0000

Data Index: 909899 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4340. Min Act: -0.0000

Data Index: 637747 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4455. Min Act: -0.0000

Data Index: 624584 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4641. Min Act: -0.0000

Data Index: 849174 (C4 (Web Text))

Max Activating Token Index: 763

Text #11

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4437. Min Act: -0.0000

Data Index: 540744 (C4 (Web Text))

Max Activating Token Index: 324

Text #12

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4431. Min Act: -0.0000

Data Index: 274911 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4400. Min Act: -0.0000

Data Index: 990001 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1145502 (C4 (Web Text))

Max Activating Token Index: 960

Text #15

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4515. Min Act: -0.0000

Data Index: 1216508 (C4 (Web Text))

Max Activating Token Index: 840

Text #16

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4649. Min Act: -0.0000

Data Index: 742866 (C4 (Web Text))

Max Activating Token Index: 264

Text #17

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4446. Min Act: -0.0000

Data Index: 665525 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.4395. Min Act: -0.0000

Data Index: 978096 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.5258. Min Range: -0.5258

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1040270 (C4 (Web Text))

Max Activating Token Index: 954