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

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

Neuron 1788 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9927. Min Act: -0.0001

Data Index: 170704 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9867. Min Act: -0.0001

Data Index: 976043 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8976. Min Act: -0.0001

Data Index: 1347849 (C4 (Web Text))

Max Activating Token Index: 194

Text #3

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.9161. Min Act: -0.0001

Data Index: 577092 (C4 (Web Text))

Max Activating Token Index: 992

Text #4

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8203. Min Act: -0.0001

Data Index: 1062003 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8485. Min Act: -0.0001

Data Index: 1019295 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7965. Min Act: -0.0001

Data Index: 294982 (C4 (Web Text))

Max Activating Token Index: 250

Text #7

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8240. Min Act: -0.0001

Data Index: 314944 (C4 (Web Text))

Max Activating Token Index: 148

Text #8

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7955. Min Act: -0.0001

Data Index: 271591 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7787. Min Act: -0.0001

Data Index: 761329 (C4 (Web Text))

Max Activating Token Index: 88

Text #10

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7812. Min Act: -0.0001

Data Index: 649271 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7753. Min Act: -0.0001

Data Index: 14069 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7767. Min Act: -0.0001

Data Index: 1359429 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8013. Min Act: -0.0001

Data Index: 261356 (C4 (Web Text))

Max Activating Token Index: 1016

Text #14

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.8071. Min Act: -0.0001

Data Index: 375526 (C4 (Web Text))

Max Activating Token Index: 456

Text #15

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7994. Min Act: -0.0001

Data Index: 1083426 (C4 (Web Text))

Max Activating Token Index: 936

Text #16

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7524. Min Act: -0.0001

Data Index: 903222 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7573. Min Act: -0.0001

Data Index: 1077691 (C4 (Web Text))

Max Activating Token Index: 90

Text #18

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7308. Min Act: -0.0001

Data Index: 1148149 (C4 (Web Text))

Max Activating Token Index: 277

Text #19

Max Range: 0.9927. Min Range: -0.9927

Max Act: 0.7482. Min Act: -0.0001

Data Index: 337864 (C4 (Web Text))

Max Activating Token Index: 503