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

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

Neuron 302 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: 0.0660. Min Range: -0.0660

Max Act: 0.0660. Min Act: -0.0004

Data Index: 939676 (C4 (Web Text))

Max Activating Token Index: 470

Text #1

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0593. Min Act: -0.0003

Data Index: 631213 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0591. Min Act: -0.0003

Data Index: 935150 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0564. Min Act: -0.0003

Data Index: 515698 (C4 (Web Text))

Max Activating Token Index: 659

Text #4

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0545. Min Act: -0.0003

Data Index: 509333 (C4 (Web Text))

Max Activating Token Index: 328

Text #5

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0539. Min Act: -0.0003

Data Index: 700905 (C4 (Web Text))

Max Activating Token Index: 110

Text #6

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0504. Min Act: -0.0003

Data Index: 808780 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0522. Min Act: -0.0003

Data Index: 523090 (C4 (Web Text))

Max Activating Token Index: 327

Text #8

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1335284 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0520. Min Act: -0.0002

Data Index: 653315 (C4 (Web Text))

Max Activating Token Index: 789

Text #10

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0506. Min Act: -0.0003

Data Index: 336184 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0495. Min Act: -0.0004

Data Index: 1143933 (C4 (Web Text))

Max Activating Token Index: 220

Text #12

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0498. Min Act: -0.0003

Data Index: 181289 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0489. Min Act: -0.0003

Data Index: 316954 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0497. Min Act: -0.0003

Data Index: 666115 (C4 (Web Text))

Max Activating Token Index: 683

Text #15

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0475. Min Act: -0.0003

Data Index: 875835 (C4 (Web Text))

Max Activating Token Index: 578

Text #16

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0445. Min Act: -0.0003

Data Index: 987300 (C4 (Web Text))

Max Activating Token Index: 628

Text #17

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0482. Min Act: -0.0003

Data Index: 590487 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0454. Min Act: -0.0003

Data Index: 424443 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.0660. Min Range: -0.0660

Max Act: 0.0463. Min Act: -0.0003

Data Index: 689002 (C4 (Web Text))

Max Activating Token Index: 998