Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 258 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1593. Min Act: -0.0004

Data Index: 293566 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1003. Min Act: -0.0004

Data Index: 998478 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.1125. Min Act: -0.0004

Data Index: 1540067 (Python Code)

Max Activating Token Index: 631

Text #3

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0998. Min Act: -0.0004

Data Index: 813355 (C4 (Web Text))

Max Activating Token Index: 221

Text #4

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0963. Min Act: -0.0004

Data Index: 987873 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0975. Min Act: -0.0004

Data Index: 1145152 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0978. Min Act: -0.0004

Data Index: 606336 (C4 (Web Text))

Max Activating Token Index: 266

Text #7

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0904. Min Act: -0.0004

Data Index: 882245 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0937. Min Act: -0.0004

Data Index: 33353 (C4 (Web Text))

Max Activating Token Index: 775

Text #9

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0934. Min Act: -0.0004

Data Index: 1271527 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0890. Min Act: -0.0004

Data Index: 1381590 (Python Code)

Max Activating Token Index: 281

Text #11

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0922. Min Act: -0.0004

Data Index: 610177 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0890. Min Act: -0.0004

Data Index: 1444239 (Python Code)

Max Activating Token Index: 795

Text #13

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0880. Min Act: -0.0004

Data Index: 1532288 (Python Code)

Max Activating Token Index: 852

Text #14

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0910. Min Act: -0.0004

Data Index: 1279822 (C4 (Web Text))

Max Activating Token Index: 409

Text #15

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0900. Min Act: -0.0004

Data Index: 659002 (C4 (Web Text))

Max Activating Token Index: 525

Text #16

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0897. Min Act: -0.0004

Data Index: 1459031 (Python Code)

Max Activating Token Index: 932

Text #17

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0932. Min Act: -0.0004

Data Index: 779235 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0834. Min Act: -0.0004

Data Index: 1562228 (Python Code)

Max Activating Token Index: 431

Text #19

Max Range: 0.1593. Min Range: -0.1593

Max Act: 0.0863. Min Act: -0.0004

Data Index: 60496 (C4 (Web Text))

Max Activating Token Index: 978