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

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

Neuron 638 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 959459 (C4 (Web Text))

Max Activating Token Index: 1

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 292386 (C4 (Web Text))

Max Activating Token Index: 1

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 257176 (C4 (Web Text))

Max Activating Token Index: 1

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 298442 (C4 (Web Text))

Max Activating Token Index: 1

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 414266 (C4 (Web Text))

Max Activating Token Index: 1

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 552630 (C4 (Web Text))

Max Activating Token Index: 1

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 785780 (C4 (Web Text))

Max Activating Token Index: 1

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 104381 (C4 (Web Text))

Max Activating Token Index: 1

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 16961 (C4 (Web Text))

Max Activating Token Index: 1

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 153357 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 991390 (C4 (Web Text))

Max Activating Token Index: 1

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1133206 (C4 (Web Text))

Max Activating Token Index: 1

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1172631 (C4 (Web Text))

Max Activating Token Index: 1

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1205897 (C4 (Web Text))

Max Activating Token Index: 1

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1229878 (C4 (Web Text))

Max Activating Token Index: 1

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0004

Data Index: 1310135 (C4 (Web Text))

Max Activating Token Index: 1

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1346202 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0260. Min Act: -0.0004

Data Index: 80591 (C4 (Web Text))

Max Activating Token Index: 1

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0260. Min Act: -0.0003

Data Index: 32175 (C4 (Web Text))

Max Activating Token Index: 1

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0260. Min Act: -0.0003

Data Index: 4013 (C4 (Web Text))

Max Activating Token Index: 1