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

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

Neuron 3472 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: 0.7723. Min Range: -0.7723

Max Act: 0.7276. Min Act: -0.0000

Data Index: 608790 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.7241. Min Act: -0.0000

Data Index: 567730 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.7723. Min Act: -0.0000

Data Index: 992023 (C4 (Web Text))

Max Activating Token Index: 392

Text #3

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6660. Min Act: -0.0000

Data Index: 469777 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6675. Min Act: -0.0000

Data Index: 791422 (C4 (Web Text))

Max Activating Token Index: 546

Text #5

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6813. Min Act: -0.0000

Data Index: 372111 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6187. Min Act: -0.0000

Data Index: 1244394 (C4 (Web Text))

Max Activating Token Index: 683

Text #7

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6990. Min Act: -0.0000

Data Index: 896610 (C4 (Web Text))

Max Activating Token Index: 876

Text #8

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6407. Min Act: -0.0000

Data Index: 519111 (C4 (Web Text))

Max Activating Token Index: 645

Text #9

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6411. Min Act: -0.0000

Data Index: 1259849 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1149619 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5771. Min Act: -0.0000

Data Index: 525040 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5829. Min Act: -0.0000

Data Index: 16367 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1008824 (C4 (Web Text))

Max Activating Token Index: 801

Text #14

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5512. Min Act: -0.0000

Data Index: 207916 (C4 (Web Text))

Max Activating Token Index: 253

Text #15

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5378. Min Act: -0.0000

Data Index: 402167 (C4 (Web Text))

Max Activating Token Index: 660

Text #16

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5481. Min Act: -0.0000

Data Index: 299182 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5733. Min Act: -0.0000

Data Index: 486964 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5566. Min Act: -0.0000

Data Index: 1131927 (C4 (Web Text))

Max Activating Token Index: 733

Text #19

Max Range: 0.7723. Min Range: -0.7723

Max Act: 0.5633. Min Act: -0.0000

Data Index: 281887 (C4 (Web Text))

Max Activating Token Index: 473