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

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

Neuron 4861 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4999. Min Range: -3.4999

Max Act: 3.4999. Min Act: -0.0000

Data Index: 1386362 (Python Code)

Max Activating Token Index: 379

Text #1

Max Range: 3.4999. Min Range: -3.4999

Max Act: 3.1092. Min Act: -0.0000

Data Index: 1216738 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.7859. Min Act: -0.0000

Data Index: 138136 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.9209. Min Act: -0.0000

Data Index: 1397660 (Python Code)

Max Activating Token Index: 71

Text #4

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.8451. Min Act: -0.0000

Data Index: 6185 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.8911. Min Act: -0.0000

Data Index: 1582750 (Python Code)

Max Activating Token Index: 1003

Text #6

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.6240. Min Act: -0.0000

Data Index: 474988 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.7215. Min Act: -0.0000

Data Index: 587782 (C4 (Web Text))

Max Activating Token Index: 469

Text #8

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.4048. Min Act: -0.0000

Data Index: 1646808 (Python Code)

Max Activating Token Index: 480

Text #9

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1392640 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.3450. Min Act: -0.0000

Data Index: 582171 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.4565. Min Act: -0.0000

Data Index: 906275 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.6001. Min Act: -0.0000

Data Index: 384748 (C4 (Web Text))

Max Activating Token Index: 401

Text #13

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.2932. Min Act: -0.0000

Data Index: 1291075 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.5282. Min Act: -0.0000

Data Index: 1398469 (Python Code)

Max Activating Token Index: 43

Text #15

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.3910. Min Act: -0.0000

Data Index: 413501 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.6335. Min Act: -0.0000

Data Index: 1020612 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.4857. Min Act: -0.0000

Data Index: 1510899 (Python Code)

Max Activating Token Index: 419

Text #18

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.3886. Min Act: -0.0000

Data Index: 1440433 (Python Code)

Max Activating Token Index: 57

Text #19

Max Range: 3.4999. Min Range: -3.4999

Max Act: 2.3988. Min Act: -0.0000

Data Index: 368064 (C4 (Web Text))

Max Activating Token Index: 576