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

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

Neuron 873 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8454. Min Act: 0.0000

Data Index: 1609452 (Python Code)

Max Activating Token Index: 352

Text #1

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8123. Min Act: -0.0000

Data Index: 484999 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8141. Min Act: 0.0000

Data Index: 1462004 (Python Code)

Max Activating Token Index: 993

Text #3

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8091. Min Act: 0.0000

Data Index: 1386543 (Python Code)

Max Activating Token Index: 619

Text #4

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.8041. Min Act: 0.0002

Data Index: 830324 (C4 (Web Text))

Max Activating Token Index: 841

Text #5

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7748. Min Act: -0.0000

Data Index: 1440476 (Python Code)

Max Activating Token Index: 989

Text #6

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7464. Min Act: -0.0000

Data Index: 1095355 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1543470 (Python Code)

Max Activating Token Index: 748

Text #8

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7589. Min Act: 0.0000

Data Index: 976643 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7480. Min Act: 0.0000

Data Index: 923112 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7118. Min Act: 0.0002

Data Index: 861709 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7274. Min Act: 0.0000

Data Index: 1498603 (Python Code)

Max Activating Token Index: 696

Text #12

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7206. Min Act: -0.0000

Data Index: 1548138 (Python Code)

Max Activating Token Index: 515

Text #13

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7447. Min Act: -0.0000

Data Index: 228614 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7615. Min Act: -0.0000

Data Index: 314344 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7087. Min Act: 0.0002

Data Index: 109365 (C4 (Web Text))

Max Activating Token Index: 194

Text #16

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7012. Min Act: -0.0000

Data Index: 952017 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7045. Min Act: -0.0000

Data Index: 187915 (C4 (Web Text))

Max Activating Token Index: 829

Text #18

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1162212 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.8454. Min Range: -0.8454

Max Act: 0.6829. Min Act: -0.0000

Data Index: 699811 (C4 (Web Text))

Max Activating Token Index: 637