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

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

Neuron 2708 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0071. Min Act: -0.0000

Data Index: 1280662 (C4 (Web Text))

Max Activating Token Index: 333

Text #1

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3717. Min Act: -0.0000

Data Index: 1049308 (C4 (Web Text))

Max Activating Token Index: 238

Text #2

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.4700. Min Act: -0.0000

Data Index: 1298358 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.3407. Min Act: -0.0000

Data Index: 742160 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.2615. Min Act: -0.0000

Data Index: 653280 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0936. Min Act: -0.0000

Data Index: 44949 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0828. Min Act: -0.0000

Data Index: 137243 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0613. Min Act: -0.0000

Data Index: 496638 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0616. Min Act: -0.0000

Data Index: 1047850 (C4 (Web Text))

Max Activating Token Index: 991

Text #9

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0553. Min Act: -0.0000

Data Index: 890086 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0612. Min Act: -0.0000

Data Index: 1153410 (C4 (Web Text))

Max Activating Token Index: 764

Text #11

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0744. Min Act: -0.0000

Data Index: 683505 (C4 (Web Text))

Max Activating Token Index: 441

Text #12

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0589. Min Act: -0.0000

Data Index: 136269 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1259620 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0492. Min Act: -0.0000

Data Index: 581990 (C4 (Web Text))

Max Activating Token Index: 290

Text #15

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0449. Min Act: -0.0000

Data Index: 879878 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0517. Min Act: -0.0000

Data Index: 564104 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0501. Min Act: -0.0000

Data Index: 628655 (C4 (Web Text))

Max Activating Token Index: 787

Text #18

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0530. Min Act: -0.0000

Data Index: 374606 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 0.4700. Min Range: -0.4700

Max Act: 0.0498. Min Act: -0.0000

Data Index: 1615772 (Python Code)

Max Activating Token Index: 30