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

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

Neuron 4438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.9416. Min Act: -0.0000

Data Index: 1013085 (C4 (Web Text))

Max Activating Token Index: 674

Text #1

Max Range: 4.1556. Min Range: -4.1556

Max Act: 4.1556. Min Act: -0.0000

Data Index: 582248 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.9527. Min Act: -0.0000

Data Index: 534748 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 4.1556. Min Range: -4.1556

Max Act: 4.0608. Min Act: -0.0000

Data Index: 521628 (C4 (Web Text))

Max Activating Token Index: 1019

Text #4

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.5211. Min Act: -0.0000

Data Index: 660784 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.6564. Min Act: -0.0000

Data Index: 179337 (C4 (Web Text))

Max Activating Token Index: 23

Text #6

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.2361. Min Act: -0.0000

Data Index: 722775 (C4 (Web Text))

Max Activating Token Index: 596

Text #7

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.9368. Min Act: -0.0000

Data Index: 1312833 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.0623. Min Act: -0.0000

Data Index: 1218235 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.9933. Min Act: -0.0001

Data Index: 950895 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.9618. Min Act: -0.0000

Data Index: 884377 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.0686. Min Act: -0.0000

Data Index: 1290547 (C4 (Web Text))

Max Activating Token Index: 20

Text #12

Max Range: 4.1556. Min Range: -4.1556

Max Act: 3.1117. Min Act: -0.0001

Data Index: 585522 (C4 (Web Text))

Max Activating Token Index: 358

Text #13

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.8204. Min Act: -0.0000

Data Index: 460364 (C4 (Web Text))

Max Activating Token Index: 639

Text #14

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.7983. Min Act: -0.0000

Data Index: 663513 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.9260. Min Act: -0.0000

Data Index: 1255297 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.7446. Min Act: -0.0000

Data Index: 582644 (C4 (Web Text))

Max Activating Token Index: 698

Text #17

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.9106. Min Act: -0.0000

Data Index: 1048432 (C4 (Web Text))

Max Activating Token Index: 887

Text #18

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.8394. Min Act: -0.0001

Data Index: 1064656 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 4.1556. Min Range: -4.1556

Max Act: 2.9618. Min Act: -0.0000

Data Index: 1193667 (C4 (Web Text))

Max Activating Token Index: 315