Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 463 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0611. Min Act: -0.0005

Data Index: 141682 (C4 (Web Text))

Max Activating Token Index: 241

Text #1

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0580. Min Act: -0.0005

Data Index: 1151090 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0569. Min Act: -0.0005

Data Index: 831102 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0566. Min Act: -0.0005

Data Index: 1304507 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0538. Min Act: -0.0005

Data Index: 378229 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0533. Min Act: -0.0005

Data Index: 532071 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0543. Min Act: -0.0005

Data Index: 271563 (C4 (Web Text))

Max Activating Token Index: 221

Text #7

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0564. Min Act: -0.0005

Data Index: 359726 (C4 (Web Text))

Max Activating Token Index: 917

Text #8

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0540. Min Act: -0.0005

Data Index: 1091146 (C4 (Web Text))

Max Activating Token Index: 277

Text #9

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0559. Min Act: -0.0005

Data Index: 156121 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0541. Min Act: -0.0005

Data Index: 865571 (C4 (Web Text))

Max Activating Token Index: 996

Text #11

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0490. Min Act: -0.0005

Data Index: 414501 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0542. Min Act: -0.0005

Data Index: 680463 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0512. Min Act: -0.0005

Data Index: 588605 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0531. Min Act: -0.0005

Data Index: 103492 (C4 (Web Text))

Max Activating Token Index: 236

Text #15

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0544. Min Act: -0.0005

Data Index: 931572 (C4 (Web Text))

Max Activating Token Index: 487

Text #16

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0528. Min Act: -0.0005

Data Index: 797571 (C4 (Web Text))

Max Activating Token Index: 614

Text #17

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0499. Min Act: -0.0005

Data Index: 498799 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0550. Min Act: -0.0005

Data Index: 385048 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 0.0611. Min Range: -0.0611

Max Act: 0.0548. Min Act: -0.0005

Data Index: 196095 (C4 (Web Text))

Max Activating Token Index: 118