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

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

Neuron 2284 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: 0.5678. Min Range: -0.5678

Max Act: 0.5678. Min Act: -0.0001

Data Index: 1605560 (Python Code)

Max Activating Token Index: 897

Text #1

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.5378. Min Act: -0.0001

Data Index: 1538903 (Python Code)

Max Activating Token Index: 839

Text #2

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.5064. Min Act: -0.0001

Data Index: 1447274 (Python Code)

Max Activating Token Index: 381

Text #3

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4499. Min Act: -0.0001

Data Index: 717208 (C4 (Web Text))

Max Activating Token Index: 958

Text #4

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4701. Min Act: -0.0001

Data Index: 1512129 (Python Code)

Max Activating Token Index: 352

Text #5

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4655. Min Act: -0.0001

Data Index: 1486291 (Python Code)

Max Activating Token Index: 492

Text #6

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1523476 (Python Code)

Max Activating Token Index: 169

Text #7

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4289. Min Act: -0.0001

Data Index: 1463161 (Python Code)

Max Activating Token Index: 640

Text #8

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1368558 (Python Code)

Max Activating Token Index: 702

Text #9

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4220. Min Act: -0.0000

Data Index: 804464 (C4 (Web Text))

Max Activating Token Index: 946

Text #10

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4464. Min Act: -0.0001

Data Index: 1149293 (C4 (Web Text))

Max Activating Token Index: 155

Text #11

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4007. Min Act: -0.0000

Data Index: 1227217 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4228. Min Act: -0.0001

Data Index: 726927 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1536932 (Python Code)

Max Activating Token Index: 984

Text #14

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3998. Min Act: -0.0000

Data Index: 576239 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1249145 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.4081. Min Act: -0.0000

Data Index: 1520410 (Python Code)

Max Activating Token Index: 235

Text #17

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3791. Min Act: -0.0001

Data Index: 1038317 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1423858 (Python Code)

Max Activating Token Index: 873

Text #19

Max Range: 0.5678. Min Range: -0.5678

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1467302 (Python Code)

Max Activating Token Index: 311