Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3987 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0585. Min Act: -0.0001

Data Index: 179281 (C4 (Web Text))

Max Activating Token Index: 89

Text #1

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0591. Min Act: -0.0001

Data Index: 219948 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0571. Min Act: -0.0001

Data Index: 64747 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0583. Min Act: -0.0001

Data Index: 480713 (C4 (Web Text))

Max Activating Token Index: 89

Text #4

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0563. Min Act: -0.0001

Data Index: 405392 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1056354 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0557. Min Act: -0.0001

Data Index: 389509 (C4 (Web Text))

Max Activating Token Index: 50

Text #7

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0562. Min Act: -0.0001

Data Index: 192753 (C4 (Web Text))

Max Activating Token Index: 640

Text #8

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0553. Min Act: -0.0001

Data Index: 18338 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0549. Min Act: -0.0001

Data Index: 633862 (C4 (Web Text))

Max Activating Token Index: 220

Text #10

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0548. Min Act: -0.0001

Data Index: 501687 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0547. Min Act: -0.0002

Data Index: 522989 (C4 (Web Text))

Max Activating Token Index: 643

Text #12

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0546. Min Act: -0.0001

Data Index: 899493 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1018287 (C4 (Web Text))

Max Activating Token Index: 302

Text #14

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0544. Min Act: -0.0001

Data Index: 58402 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0541. Min Act: -0.0001

Data Index: 256724 (C4 (Web Text))

Max Activating Token Index: 850

Text #16

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0545. Min Act: -0.0001

Data Index: 370886 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0537. Min Act: -0.0001

Data Index: 657903 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0541. Min Act: -0.0001

Data Index: 527782 (C4 (Web Text))

Max Activating Token Index: 20

Text #19

Max Range: 0.0591. Min Range: -0.0591

Max Act: 0.0532. Min Act: -0.0001

Data Index: 1242020 (C4 (Web Text))

Max Activating Token Index: 901