Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2665 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.7299. Min Act: -0.0001

Data Index: 1474800 (Python Code)

Max Activating Token Index: 864

Text #1

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4599. Min Act: -0.0001

Data Index: 1547435 (Python Code)

Max Activating Token Index: 72

Text #2

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4161. Min Act: -0.0001

Data Index: 1502122 (Python Code)

Max Activating Token Index: 836

Text #3

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4263. Min Act: -0.0001

Data Index: 1537103 (Python Code)

Max Activating Token Index: 458

Text #4

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4531. Min Act: -0.0001

Data Index: 1410530 (Python Code)

Max Activating Token Index: 887

Text #5

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1492885 (Python Code)

Max Activating Token Index: 267

Text #6

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4078. Min Act: -0.0001

Data Index: 1551339 (Python Code)

Max Activating Token Index: 205

Text #7

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3847. Min Act: -0.0001

Data Index: 1431975 (Python Code)

Max Activating Token Index: 188

Text #8

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4013. Min Act: -0.0000

Data Index: 1603449 (Python Code)

Max Activating Token Index: 250

Text #9

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3907. Min Act: -0.0001

Data Index: 1568254 (Python Code)

Max Activating Token Index: 180

Text #10

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4111. Min Act: -0.0001

Data Index: 1429905 (Python Code)

Max Activating Token Index: 660

Text #11

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3726. Min Act: -0.0001

Data Index: 1389262 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1553927 (Python Code)

Max Activating Token Index: 166

Text #13

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4109. Min Act: -0.0001

Data Index: 1419084 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3890. Min Act: -0.0001

Data Index: 1361013 (Python Code)

Max Activating Token Index: 440

Text #15

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3935. Min Act: -0.0001

Data Index: 1417544 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.4058. Min Act: -0.0001

Data Index: 1433220 (Python Code)

Max Activating Token Index: 598

Text #17

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3849. Min Act: -0.0001

Data Index: 599237 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3817. Min Act: -0.0001

Data Index: 1654946 (Python Code)

Max Activating Token Index: 697

Text #19

Max Range: 0.7299. Min Range: -0.7299

Max Act: 0.3798. Min Act: -0.0001

Data Index: 1559593 (Python Code)

Max Activating Token Index: 899