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

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

Neuron 3641 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0585. Min Act: -0.0001

Data Index: 614236 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0569. Min Act: -0.0001

Data Index: 346731 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0571. Min Act: -0.0001

Data Index: 435828 (C4 (Web Text))

Max Activating Token Index: 892

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0590. Min Act: -0.0001

Data Index: 621600 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1136602 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0001

Data Index: 436479 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0580. Min Act: -0.0001

Data Index: 357769 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0521. Min Act: -0.0001

Data Index: 798181 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0545. Min Act: -0.0001

Data Index: 586669 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0538. Min Act: -0.0001

Data Index: 122018 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0514. Min Act: -0.0001

Data Index: 660517 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0547. Min Act: -0.0001

Data Index: 841321 (C4 (Web Text))

Max Activating Token Index: 132

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1236825 (C4 (Web Text))

Max Activating Token Index: 960

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0564. Min Act: -0.0001

Data Index: 239426 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0503. Min Act: -0.0001

Data Index: 433726 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0550. Min Act: -0.0001

Data Index: 158427 (C4 (Web Text))

Max Activating Token Index: 667

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0552. Min Act: -0.0001

Data Index: 390236 (C4 (Web Text))

Max Activating Token Index: 267

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0511. Min Act: -0.0001

Data Index: 520997 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0516. Min Act: -0.0001

Data Index: 813888 (C4 (Web Text))

Max Activating Token Index: 483

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0448. Min Act: -0.0001

Data Index: 481625 (C4 (Web Text))

Max Activating Token Index: 621