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

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

Neuron 555 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0820. Min Range: -1.0820

Max Act: 1.0820. Min Act: -0.0000

Data Index: 617078 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9705. Min Act: -0.0000

Data Index: 749531 (C4 (Web Text))

Max Activating Token Index: 447

Text #2

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9732. Min Act: -0.0000

Data Index: 1293409 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9764. Min Act: 0.0000

Data Index: 384664 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9103. Min Act: -0.0000

Data Index: 1486487 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8891. Min Act: -0.0000

Data Index: 642626 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8045. Min Act: 0.0000

Data Index: 290486 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7940. Min Act: 0.0000

Data Index: 216008 (C4 (Web Text))

Max Activating Token Index: 31

Text #8

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7735. Min Act: -0.0000

Data Index: 1322944 (C4 (Web Text))

Max Activating Token Index: 682

Text #9

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7168. Min Act: -0.0000

Data Index: 713650 (C4 (Web Text))

Max Activating Token Index: 43

Text #10

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7687. Min Act: -0.0000

Data Index: 691146 (C4 (Web Text))

Max Activating Token Index: 464

Text #11

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7406. Min Act: -0.0000

Data Index: 418158 (C4 (Web Text))

Max Activating Token Index: 38

Text #12

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7448. Min Act: 0.0000

Data Index: 1316937 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1533249 (Python Code)

Max Activating Token Index: 429

Text #14

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6947. Min Act: -0.0000

Data Index: 1143034 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7373. Min Act: 0.0001

Data Index: 1189613 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7031. Min Act: -0.0000

Data Index: 171722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6949. Min Act: 0.0000

Data Index: 366751 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6874. Min Act: -0.0000

Data Index: 882977 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.6903. Min Act: -0.0000

Data Index: 1078032 (C4 (Web Text))

Max Activating Token Index: 139