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

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

Neuron 3654 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0798. Min Act: -0.0002

Data Index: 137807 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0629. Min Act: -0.0002

Data Index: 698489 (C4 (Web Text))

Max Activating Token Index: 878

Text #2

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0522. Min Act: -0.0002

Data Index: 242266 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0615. Min Act: -0.0002

Data Index: 602936 (C4 (Web Text))

Max Activating Token Index: 684

Text #4

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0630. Min Act: -0.0002

Data Index: 603224 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1357189 (C4 (Web Text))

Max Activating Token Index: 337

Text #6

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0599. Min Act: -0.0002

Data Index: 1142689 (C4 (Web Text))

Max Activating Token Index: 970

Text #7

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0582. Min Act: -0.0002

Data Index: 998213 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1308035 (C4 (Web Text))

Max Activating Token Index: 801

Text #9

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0534. Min Act: -0.0002

Data Index: 666718 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0523. Min Act: -0.0002

Data Index: 161046 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1055824 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0544. Min Act: -0.0002

Data Index: 986476 (C4 (Web Text))

Max Activating Token Index: 67

Text #13

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0573. Min Act: -0.0002

Data Index: 427696 (C4 (Web Text))

Max Activating Token Index: 751

Text #14

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0526. Min Act: -0.0002

Data Index: 1090123 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0554. Min Act: -0.0002

Data Index: 429614 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0497. Min Act: -0.0002

Data Index: 943406 (C4 (Web Text))

Max Activating Token Index: 211

Text #17

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0564. Min Act: -0.0002

Data Index: 604575 (C4 (Web Text))

Max Activating Token Index: 593

Text #18

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0530. Min Act: -0.0002

Data Index: 92927 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.0798. Min Range: -0.0798

Max Act: 0.0550. Min Act: -0.0002

Data Index: 763136 (C4 (Web Text))

Max Activating Token Index: 367