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

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

Neuron 1666 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0637. Min Act: -0.0001

Data Index: 966368 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0627. Min Act: -0.0001

Data Index: 1149668 (C4 (Web Text))

Max Activating Token Index: 833

Text #2

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0612. Min Act: -0.0001

Data Index: 927277 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1509259 (Python Code)

Max Activating Token Index: 353

Text #4

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1410655 (Python Code)

Max Activating Token Index: 905

Text #5

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0571. Min Act: -0.0001

Data Index: 384495 (C4 (Web Text))

Max Activating Token Index: 519

Text #6

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0576. Min Act: -0.0001

Data Index: 310909 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0547. Min Act: -0.0001

Data Index: 1254844 (C4 (Web Text))

Max Activating Token Index: 113

Text #8

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0522. Min Act: -0.0001

Data Index: 608824 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0531. Min Act: -0.0002

Data Index: 512029 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1116171 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0501. Min Act: -0.0001

Data Index: 1034667 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0513. Min Act: -0.0001

Data Index: 1412524 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0515. Min Act: -0.0002

Data Index: 856199 (C4 (Web Text))

Max Activating Token Index: 401

Text #14

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1126868 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0519. Min Act: -0.0001

Data Index: 265502 (C4 (Web Text))

Max Activating Token Index: 884

Text #16

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0523. Min Act: -0.0001

Data Index: 688847 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0499. Min Act: -0.0001

Data Index: 359717 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1572882 (Python Code)

Max Activating Token Index: 455

Text #19

Max Range: 0.0637. Min Range: -0.0637

Max Act: 0.0482. Min Act: -0.0001

Data Index: 892901 (C4 (Web Text))

Max Activating Token Index: 589