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

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

Neuron 3185 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.7853. Min Act: -0.0001

Data Index: 276093 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.8092. Min Act: -0.0001

Data Index: 709641 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.7860. Min Act: -0.0001

Data Index: 1023739 (C4 (Web Text))

Max Activating Token Index: 277

Text #3

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.8370. Min Act: -0.0001

Data Index: 1300689 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.7533. Min Act: -0.0001

Data Index: 888411 (C4 (Web Text))

Max Activating Token Index: 839

Text #5

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.7163. Min Act: -0.0001

Data Index: 796912 (C4 (Web Text))

Max Activating Token Index: 913

Text #6

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.7567. Min Act: -0.0001

Data Index: 936537 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.7481. Min Act: -0.0001

Data Index: 727512 (C4 (Web Text))

Max Activating Token Index: 220

Text #8

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6863. Min Act: -0.0001

Data Index: 265195 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.7033. Min Act: -0.0001

Data Index: 323815 (C4 (Web Text))

Max Activating Token Index: 629

Text #10

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6559. Min Act: -0.0001

Data Index: 757263 (C4 (Web Text))

Max Activating Token Index: 507

Text #11

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6662. Min Act: -0.0001

Data Index: 869063 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6802. Min Act: -0.0001

Data Index: 361558 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6991. Min Act: -0.0001

Data Index: 433891 (C4 (Web Text))

Max Activating Token Index: 298

Text #14

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6711. Min Act: -0.0001

Data Index: 279128 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6425. Min Act: -0.0001

Data Index: 990013 (C4 (Web Text))

Max Activating Token Index: 604

Text #16

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6583. Min Act: -0.0001

Data Index: 262411 (C4 (Web Text))

Max Activating Token Index: 848

Text #17

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6338. Min Act: -0.0000

Data Index: 1145329 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6684. Min Act: -0.0000

Data Index: 566131 (C4 (Web Text))

Max Activating Token Index: 881

Text #19

Max Range: 0.8370. Min Range: -0.8370

Max Act: 0.6500. Min Act: -0.0001

Data Index: 1296878 (C4 (Web Text))

Max Activating Token Index: 477