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

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

Neuron 816 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: 1.3003. Min Range: -1.3003

Max Act: 1.3003. Min Act: -0.0000

Data Index: 1375741 (Python Code)

Max Activating Token Index: 977

Text #1

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1484. Min Act: -0.0000

Data Index: 1453453 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.2153. Min Act: -0.0000

Data Index: 1562280 (Python Code)

Max Activating Token Index: 62

Text #3

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1108. Min Act: -0.0000

Data Index: 1634618 (Python Code)

Max Activating Token Index: 576

Text #4

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1541636 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0874. Min Act: -0.0000

Data Index: 349134 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1079. Min Act: -0.0000

Data Index: 1403603 (Python Code)

Max Activating Token Index: 188

Text #7

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.1255. Min Act: -0.0000

Data Index: 1463537 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0863. Min Act: -0.0000

Data Index: 1504698 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0943. Min Act: -0.0000

Data Index: 1453519 (Python Code)

Max Activating Token Index: 19

Text #10

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9769. Min Act: -0.0000

Data Index: 1561154 (Python Code)

Max Activating Token Index: 97

Text #11

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0063. Min Act: -0.0000

Data Index: 1524729 (Python Code)

Max Activating Token Index: 135

Text #12

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0294. Min Act: -0.0000

Data Index: 1373011 (Python Code)

Max Activating Token Index: 732

Text #13

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0662. Min Act: -0.0000

Data Index: 1167525 (C4 (Web Text))

Max Activating Token Index: 192

Text #14

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1412660 (Python Code)

Max Activating Token Index: 340

Text #15

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9557. Min Act: -0.0000

Data Index: 1367325 (Python Code)

Max Activating Token Index: 177

Text #16

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9606. Min Act: -0.0000

Data Index: 1369276 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9243. Min Act: -0.0000

Data Index: 1523386 (Python Code)

Max Activating Token Index: 630

Text #18

Max Range: 1.3003. Min Range: -1.3003

Max Act: 1.0051. Min Act: -0.0000

Data Index: 262201 (C4 (Web Text))

Max Activating Token Index: 808

Text #19

Max Range: 1.3003. Min Range: -1.3003

Max Act: 0.9585. Min Act: -0.0000

Data Index: 914679 (C4 (Web Text))

Max Activating Token Index: 488