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

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

Neuron 1398 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.7571. Min Act: -0.0001

Data Index: 328769 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.7491. Min Act: -0.0001

Data Index: 508702 (C4 (Web Text))

Max Activating Token Index: 563

Text #2

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.8404. Min Act: -0.0001

Data Index: 1019693 (C4 (Web Text))

Max Activating Token Index: 799

Text #3

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1046. Min Act: -0.0001

Data Index: 75557 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1800. Min Act: -0.0001

Data Index: 194463 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1712. Min Act: -0.0001

Data Index: 151927 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1644. Min Act: -0.0001

Data Index: 545834 (C4 (Web Text))

Max Activating Token Index: 543

Text #7

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1353. Min Act: -0.0001

Data Index: 393493 (C4 (Web Text))

Max Activating Token Index: 901

Text #8

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.0359. Min Act: -0.0001

Data Index: 1029584 (C4 (Web Text))

Max Activating Token Index: 615

Text #9

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1225. Min Act: -0.0001

Data Index: 393035 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.1667. Min Act: -0.0001

Data Index: 742381 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.0249. Min Act: -0.0001

Data Index: 636997 (C4 (Web Text))

Max Activating Token Index: 281

Text #12

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.0303. Min Act: -0.0001

Data Index: 639996 (C4 (Web Text))

Max Activating Token Index: 555

Text #13

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.9852. Min Act: -0.0001

Data Index: 633547 (C4 (Web Text))

Max Activating Token Index: 350

Text #14

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.2528. Min Act: -0.0001

Data Index: 163594 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.2419. Min Act: -0.0001

Data Index: 272019 (C4 (Web Text))

Max Activating Token Index: 805

Text #16

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.2374. Min Act: -0.0001

Data Index: 949279 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.3499. Min Act: -0.0001

Data Index: 1128836 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 2.7571. Min Range: -2.7571

Max Act: 2.0450. Min Act: -0.0001

Data Index: 407443 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 2.7571. Min Range: -2.7571

Max Act: 1.6118. Min Act: -0.0001

Data Index: 320316 (C4 (Web Text))

Max Activating Token Index: 225