Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2008 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0520. Min Act: -0.0001

Data Index: 579350 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0477. Min Act: -0.0001

Data Index: 750744 (C4 (Web Text))

Max Activating Token Index: 860

Text #2

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0522. Min Act: -0.0001

Data Index: 978335 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0454. Min Act: -0.0001

Data Index: 906985 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0449. Min Act: -0.0001

Data Index: 543571 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0455. Min Act: -0.0001

Data Index: 648905 (C4 (Web Text))

Max Activating Token Index: 779

Text #6

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0460. Min Act: -0.0001

Data Index: 354931 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0479. Min Act: -0.0001

Data Index: 373368 (C4 (Web Text))

Max Activating Token Index: 979

Text #8

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0452. Min Act: -0.0001

Data Index: 150606 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0444. Min Act: -0.0001

Data Index: 858352 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0436. Min Act: -0.0001

Data Index: 722634 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0427. Min Act: -0.0001

Data Index: 449655 (C4 (Web Text))

Max Activating Token Index: 685

Text #12

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0436. Min Act: -0.0001

Data Index: 1182265 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0405. Min Act: -0.0001

Data Index: 619659 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0440. Min Act: -0.0001

Data Index: 133128 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1107742 (C4 (Web Text))

Max Activating Token Index: 708

Text #16

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0422. Min Act: -0.0001

Data Index: 319915 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0417. Min Act: -0.0001

Data Index: 261010 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0412. Min Act: -0.0001

Data Index: 685571 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.0522. Min Range: -0.0522

Max Act: 0.0375. Min Act: -0.0001

Data Index: 160520 (C4 (Web Text))

Max Activating Token Index: 691