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

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

Neuron 2463 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: -0.0001

Data Index: 1120860 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5143. Min Act: -0.0001

Data Index: 230963 (C4 (Web Text))

Max Activating Token Index: 365

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5810. Min Act: -0.0002

Data Index: 728125 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5480. Min Act: -0.0002

Data Index: 103157 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5126. Min Act: -0.0002

Data Index: 955327 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5397. Min Act: -0.0002

Data Index: 954291 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5016. Min Act: -0.0002

Data Index: 676586 (C4 (Web Text))

Max Activating Token Index: 993

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4904. Min Act: -0.0001

Data Index: 1077534 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4623. Min Act: -0.0001

Data Index: 534807 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5038. Min Act: -0.0002

Data Index: 1297525 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4944. Min Act: -0.0002

Data Index: 1320012 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4772. Min Act: -0.0001

Data Index: 126848 (C4 (Web Text))

Max Activating Token Index: 67

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4934. Min Act: -0.0002

Data Index: 1260696 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4187. Min Act: -0.0002

Data Index: 1180163 (C4 (Web Text))

Max Activating Token Index: 610

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4714. Min Act: -0.0002

Data Index: 117543 (C4 (Web Text))

Max Activating Token Index: 797

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4967. Min Act: -0.0001

Data Index: 342127 (C4 (Web Text))

Max Activating Token Index: 6

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4840. Min Act: -0.0002

Data Index: 369834 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4645. Min Act: -0.0001

Data Index: 615482 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4755. Min Act: -0.0002

Data Index: 775636 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5006. Min Act: -0.0001

Data Index: 1327426 (C4 (Web Text))

Max Activating Token Index: 451