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

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

Neuron 3965 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0899. Min Act: -0.0001

Data Index: 26660 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0712. Min Act: -0.0001

Data Index: 783358 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0683. Min Act: -0.0001

Data Index: 391667 (C4 (Web Text))

Max Activating Token Index: 313

Text #3

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0670. Min Act: -0.0001

Data Index: 388561 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0630. Min Act: -0.0001

Data Index: 699306 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0650. Min Act: -0.0001

Data Index: 329841 (C4 (Web Text))

Max Activating Token Index: 398

Text #6

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0637. Min Act: -0.0001

Data Index: 243902 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0601. Min Act: -0.0001

Data Index: 28203 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0600. Min Act: -0.0001

Data Index: 1133034 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0561. Min Act: -0.0001

Data Index: 699950 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0573. Min Act: -0.0001

Data Index: 317056 (C4 (Web Text))

Max Activating Token Index: 588

Text #11

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0569. Min Act: -0.0001

Data Index: 907962 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0548. Min Act: -0.0001

Data Index: 147803 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0570. Min Act: -0.0001

Data Index: 1310770 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0509. Min Act: -0.0001

Data Index: 950210 (C4 (Web Text))

Max Activating Token Index: 342

Text #15

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0510. Min Act: -0.0001

Data Index: 742479 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0541. Min Act: -0.0001

Data Index: 1636611 (Python Code)

Max Activating Token Index: 257

Text #17

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0641. Min Act: -0.0001

Data Index: 437925 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1196451 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 0.0899. Min Range: -0.0899

Max Act: 0.0517. Min Act: -0.0001

Data Index: 782352 (C4 (Web Text))

Max Activating Token Index: 794