Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 913 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0902. Min Act: -0.0001

Data Index: 606005 (C4 (Web Text))

Max Activating Token Index: 198

Text #1

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0720. Min Act: -0.0001

Data Index: 162877 (C4 (Web Text))

Max Activating Token Index: 361

Text #2

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0636. Min Act: -0.0001

Data Index: 415229 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0570. Min Act: -0.0001

Data Index: 319915 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1586329 (Python Code)

Max Activating Token Index: 734

Text #5

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0573. Min Act: -0.0001

Data Index: 1504937 (Python Code)

Max Activating Token Index: 797

Text #6

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1417653 (Python Code)

Max Activating Token Index: 513

Text #7

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0527. Min Act: -0.0001

Data Index: 359757 (C4 (Web Text))

Max Activating Token Index: 716

Text #8

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0549. Min Act: -0.0001

Data Index: 162398 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0539. Min Act: -0.0001

Data Index: 877650 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0534. Min Act: -0.0001

Data Index: 415917 (C4 (Web Text))

Max Activating Token Index: 355

Text #11

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0502. Min Act: -0.0001

Data Index: 899022 (C4 (Web Text))

Max Activating Token Index: 910

Text #12

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0518. Min Act: -0.0001

Data Index: 198255 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0493. Min Act: -0.0001

Data Index: 419551 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1379775 (Python Code)

Max Activating Token Index: 486

Text #15

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0509. Min Act: -0.0001

Data Index: 800681 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1003118 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0502. Min Act: -0.0001

Data Index: 1216616 (C4 (Web Text))

Max Activating Token Index: 355

Text #18

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0506. Min Act: -0.0001

Data Index: 1132201 (C4 (Web Text))

Max Activating Token Index: 107

Text #19

Max Range: 0.0902. Min Range: -0.0902

Max Act: 0.0488. Min Act: -0.0001

Data Index: 283529 (C4 (Web Text))

Max Activating Token Index: 790