Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1955 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.8895. Min Act: -0.0001

Data Index: 570411 (C4 (Web Text))

Max Activating Token Index: 473

Text #1

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.9522. Min Act: -0.0001

Data Index: 999046 (C4 (Web Text))

Max Activating Token Index: 359

Text #2

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.8113. Min Act: -0.0001

Data Index: 735348 (C4 (Web Text))

Max Activating Token Index: 561

Text #3

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.8588. Min Act: -0.0001

Data Index: 1321539 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.8007. Min Act: -0.0001

Data Index: 453883 (C4 (Web Text))

Max Activating Token Index: 347

Text #5

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.6911. Min Act: -0.0001

Data Index: 1193162 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.6012. Min Act: -0.0001

Data Index: 1066971 (C4 (Web Text))

Max Activating Token Index: 598

Text #7

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.4848. Min Act: -0.0001

Data Index: 230407 (C4 (Web Text))

Max Activating Token Index: 279

Text #8

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.3647. Min Act: -0.0001

Data Index: 112730 (C4 (Web Text))

Max Activating Token Index: 790

Text #9

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.0562. Min Act: -0.0000

Data Index: 384436 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 1.9522. Min Range: -1.9522

Max Act: 0.9751. Min Act: -0.0000

Data Index: 156291 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.0708. Min Act: -0.0001

Data Index: 805249 (C4 (Web Text))

Max Activating Token Index: 949

Text #12

Max Range: 1.9522. Min Range: -1.9522

Max Act: 0.9891. Min Act: -0.0000

Data Index: 1231586 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 1.9522. Min Range: -1.9522

Max Act: 0.9962. Min Act: -0.0000

Data Index: 820797 (C4 (Web Text))

Max Activating Token Index: 200

Text #14

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.0155. Min Act: -0.0001

Data Index: 558441 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 1.9522. Min Range: -1.9522

Max Act: 1.0111. Min Act: -0.0001

Data Index: 24506 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 1.9522. Min Range: -1.9522

Max Act: 0.9488. Min Act: -0.0000

Data Index: 897730 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 1.9522. Min Range: -1.9522

Max Act: 0.9314. Min Act: -0.0001

Data Index: 1297573 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 1.9522. Min Range: -1.9522

Max Act: 0.9050. Min Act: -0.0000

Data Index: 824617 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 1.9522. Min Range: -1.9522

Max Act: 0.8902. Min Act: -0.0000

Data Index: 592253 (C4 (Web Text))

Max Activating Token Index: 248