Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 243 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0616. Min Act: -0.0003

Data Index: 745353 (C4 (Web Text))

Max Activating Token Index: 653

Text #1

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0606. Min Act: -0.0003

Data Index: 806485 (C4 (Web Text))

Max Activating Token Index: 705

Text #2

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0592. Min Act: -0.0003

Data Index: 92357 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0535. Min Act: -0.0004

Data Index: 1260262 (C4 (Web Text))

Max Activating Token Index: 323

Text #4

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0503. Min Act: -0.0003

Data Index: 1260674 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0519. Min Act: -0.0003

Data Index: 179043 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1345008 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0507. Min Act: -0.0004

Data Index: 1075147 (C4 (Web Text))

Max Activating Token Index: 822

Text #8

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0530. Min Act: -0.0003

Data Index: 406770 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0520. Min Act: -0.0003

Data Index: 608462 (C4 (Web Text))

Max Activating Token Index: 613

Text #10

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0536. Min Act: -0.0003

Data Index: 1260898 (C4 (Web Text))

Max Activating Token Index: 681

Text #11

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 403

Text #12

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0512. Min Act: -0.0004

Data Index: 977901 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0513. Min Act: -0.0004

Data Index: 413436 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0499. Min Act: -0.0004

Data Index: 93392 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0529. Min Act: -0.0003

Data Index: 365875 (C4 (Web Text))

Max Activating Token Index: 746

Text #16

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0500. Min Act: -0.0003

Data Index: 432877 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0493. Min Act: -0.0003

Data Index: 48054 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0497. Min Act: -0.0003

Data Index: 1055919 (C4 (Web Text))

Max Activating Token Index: 345

Text #19

Max Range: 0.0616. Min Range: -0.0616

Max Act: 0.0499. Min Act: -0.0003

Data Index: 207115 (C4 (Web Text))

Max Activating Token Index: 486