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

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

Neuron 31 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.2656. Min Act: -0.0000

Data Index: 1583581 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.2243. Min Act: -0.0000

Data Index: 1467239 (Python Code)

Max Activating Token Index: 27

Text #2

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.0664. Min Act: -0.0000

Data Index: 1416223 (Python Code)

Max Activating Token Index: 407

Text #3

Max Range: 3.2656. Min Range: -3.2656

Max Act: 3.1798. Min Act: -0.0000

Data Index: 1566123 (Python Code)

Max Activating Token Index: 689

Text #4

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.9159. Min Act: -0.0000

Data Index: 1364103 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.6632. Min Act: -0.0000

Data Index: 1652880 (Python Code)

Max Activating Token Index: 128

Text #6

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.5994. Min Act: -0.0000

Data Index: 1584591 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.6530. Min Act: -0.0000

Data Index: 1433747 (Python Code)

Max Activating Token Index: 267

Text #8

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.6082. Min Act: -0.0000

Data Index: 1432945 (Python Code)

Max Activating Token Index: 415

Text #9

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.7244. Min Act: -0.0000

Data Index: 1441883 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.8673. Min Act: -0.0000

Data Index: 1566879 (Python Code)

Max Activating Token Index: 879

Text #11

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.7186. Min Act: -0.0000

Data Index: 1613026 (Python Code)

Max Activating Token Index: 822

Text #12

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.4417. Min Act: -0.0000

Data Index: 1438464 (Python Code)

Max Activating Token Index: 245

Text #13

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.8122. Min Act: -0.0000

Data Index: 1378195 (Python Code)

Max Activating Token Index: 604

Text #14

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.6940. Min Act: -0.0000

Data Index: 1476016 (Python Code)

Max Activating Token Index: 845

Text #15

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.6293. Min Act: -0.0000

Data Index: 1530877 (Python Code)

Max Activating Token Index: 572

Text #16

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.5082. Min Act: -0.0000

Data Index: 1553182 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.4972. Min Act: -0.0000

Data Index: 1642183 (Python Code)

Max Activating Token Index: 983

Text #18

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.6033. Min Act: -0.0000

Data Index: 1572270 (Python Code)

Max Activating Token Index: 729

Text #19

Max Range: 3.2656. Min Range: -3.2656

Max Act: 2.4441. Min Act: -0.0000

Data Index: 1588512 (Python Code)

Max Activating Token Index: 185