Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4067 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9849. Min Act: -0.0000

Data Index: 745070 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8892. Min Act: -0.0000

Data Index: 348418 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.9121. Min Act: -0.0000

Data Index: 268961 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7906. Min Act: -0.0000

Data Index: 1384480 (Python Code)

Max Activating Token Index: 39

Text #4

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8245. Min Act: -0.0000

Data Index: 174415 (C4 (Web Text))

Max Activating Token Index: 759

Text #5

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.7498. Min Act: -0.0000

Data Index: 43093 (C4 (Web Text))

Max Activating Token Index: 55

Text #6

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.8102. Min Act: -0.0000

Data Index: 202132 (C4 (Web Text))

Max Activating Token Index: 880

Text #7

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6776. Min Act: -0.0000

Data Index: 1303005 (C4 (Web Text))

Max Activating Token Index: 942

Text #8

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6509. Min Act: -0.0000

Data Index: 1239193 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6774. Min Act: -0.0000

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 766

Text #10

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1128241 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1338199 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6472. Min Act: -0.0000

Data Index: 714285 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6006. Min Act: -0.0000

Data Index: 377198 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6587. Min Act: -0.0000

Data Index: 411508 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.5616. Min Act: -0.0000

Data Index: 1239075 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.5893. Min Act: -0.0000

Data Index: 745638 (C4 (Web Text))

Max Activating Token Index: 70

Text #17

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.6630. Min Act: -0.0000

Data Index: 593088 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.5947. Min Act: -0.0000

Data Index: 746927 (C4 (Web Text))

Max Activating Token Index: 128

Text #19

Max Range: 0.9849. Min Range: -0.9849

Max Act: 0.5822. Min Act: -0.0000

Data Index: 3230 (C4 (Web Text))

Max Activating Token Index: 478