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

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

Neuron 2397 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0438. Min Act: -0.0001

Data Index: 939586 (C4 (Web Text))

Max Activating Token Index: 585

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0387. Min Act: -0.0001

Data Index: 484812 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0427. Min Act: -0.0001

Data Index: 794742 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0384. Min Act: -0.0001

Data Index: 315250 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0432. Min Act: -0.0001

Data Index: 1037259 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0393. Min Act: -0.0001

Data Index: 248208 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0001

Data Index: 745258 (C4 (Web Text))

Max Activating Token Index: 535

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0443. Min Act: -0.0001

Data Index: 415416 (C4 (Web Text))

Max Activating Token Index: 565

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0404. Min Act: -0.0001

Data Index: 336167 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0379. Min Act: -0.0001

Data Index: 276171 (C4 (Web Text))

Max Activating Token Index: 713

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0353. Min Act: -0.0001

Data Index: 1004893 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0451. Min Act: -0.0001

Data Index: 387878 (C4 (Web Text))

Max Activating Token Index: 741

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0409. Min Act: -0.0001

Data Index: 102787 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0387. Min Act: -0.0001

Data Index: 635825 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0358. Min Act: -0.0001

Data Index: 1245782 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1208998 (C4 (Web Text))

Max Activating Token Index: 413

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0393. Min Act: -0.0001

Data Index: 497843 (C4 (Web Text))

Max Activating Token Index: 655

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0462. Min Act: -0.0001

Data Index: 404826 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0347. Min Act: -0.0001

Data Index: 92846 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0352. Min Act: -0.0001

Data Index: 160709 (C4 (Web Text))

Max Activating Token Index: 432