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

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

Neuron 2926 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0001

Data Index: 616033 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0633. Min Act: 0.0000

Data Index: 699278 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0635. Min Act: 0.0000

Data Index: 382390 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0608. Min Act: -0.0000

Data Index: 719443 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1122927 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0521. Min Act: -0.0001

Data Index: 1256044 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0523. Min Act: 0.0000

Data Index: 131074 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0486. Min Act: -0.0001

Data Index: 1137023 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0526. Min Act: -0.0000

Data Index: 1345330 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0500. Min Act: -0.0000

Data Index: 1025029 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0521. Min Act: -0.0001

Data Index: 427163 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0513. Min Act: -0.0001

Data Index: 770787 (C4 (Web Text))

Max Activating Token Index: 624

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0495. Min Act: -0.0000

Data Index: 983449 (C4 (Web Text))

Max Activating Token Index: 64

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0511. Min Act: -0.0001

Data Index: 581705 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0436. Min Act: -0.0001

Data Index: 39845 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0469. Min Act: -0.0001

Data Index: 684881 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0494. Min Act: -0.0001

Data Index: 571753 (C4 (Web Text))

Max Activating Token Index: 277

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0461. Min Act: -0.0000

Data Index: 258886 (C4 (Web Text))

Max Activating Token Index: 73

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1263087 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0464. Min Act: -0.0001

Data Index: 760625 (C4 (Web Text))

Max Activating Token Index: 443