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

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

Neuron 605 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2016. Min Range: -1.2016

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1361754 (Python Code)

Max Activating Token Index: 375

Text #1

Max Range: 1.2016. Min Range: -1.2016

Max Act: 1.2016. Min Act: -0.0000

Data Index: 1429134 (Python Code)

Max Activating Token Index: 904

Text #2

Max Range: 1.2016. Min Range: -1.2016

Max Act: 1.1216. Min Act: -0.0000

Data Index: 1638954 (Python Code)

Max Activating Token Index: 1003

Text #3

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9927. Min Act: -0.0000

Data Index: 1539375 (Python Code)

Max Activating Token Index: 844

Text #4

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9711. Min Act: -0.0001

Data Index: 1535511 (Python Code)

Max Activating Token Index: 242

Text #5

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1545300 (Python Code)

Max Activating Token Index: 429

Text #6

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9663. Min Act: -0.0000

Data Index: 1514086 (Python Code)

Max Activating Token Index: 374

Text #7

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9594. Min Act: -0.0001

Data Index: 1584083 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9425. Min Act: -0.0001

Data Index: 1586850 (Python Code)

Max Activating Token Index: 956

Text #9

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1366923 (Python Code)

Max Activating Token Index: 80

Text #10

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.8579. Min Act: -0.0001

Data Index: 1522139 (Python Code)

Max Activating Token Index: 382

Text #11

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1612979 (Python Code)

Max Activating Token Index: 879

Text #12

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1391364 (Python Code)

Max Activating Token Index: 1019

Text #13

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9103. Min Act: -0.0001

Data Index: 1632080 (Python Code)

Max Activating Token Index: 168

Text #14

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9132. Min Act: -0.0000

Data Index: 1611327 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.9067. Min Act: -0.0000

Data Index: 1656265 (Python Code)

Max Activating Token Index: 447

Text #16

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.8925. Min Act: -0.0001

Data Index: 1387633 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.8683. Min Act: -0.0000

Data Index: 1517923 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1551481 (Python Code)

Max Activating Token Index: 799

Text #19

Max Range: 1.2016. Min Range: -1.2016

Max Act: 0.8160. Min Act: -0.0000

Data Index: 1406427 (Python Code)

Max Activating Token Index: 158