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

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

Neuron 2085 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.8501. Min Act: -0.0001

Data Index: 569933 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7824. Min Act: -0.0001

Data Index: 716721 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7788. Min Act: -0.0001

Data Index: 153690 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7798. Min Act: -0.0001

Data Index: 313350 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7286. Min Act: -0.0001

Data Index: 203120 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.7105. Min Act: -0.0001

Data Index: 292873 (C4 (Web Text))

Max Activating Token Index: 164

Text #6

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6790. Min Act: -0.0001

Data Index: 743242 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6722. Min Act: -0.0001

Data Index: 24665 (C4 (Web Text))

Max Activating Token Index: 380

Text #8

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.6725. Min Act: -0.0001

Data Index: 825263 (C4 (Web Text))

Max Activating Token Index: 351

Text #9

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.5535. Min Act: -0.0000

Data Index: 309591 (C4 (Web Text))

Max Activating Token Index: 968

Text #10

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.5062. Min Act: -0.0000

Data Index: 10496 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4737. Min Act: -0.0000

Data Index: 974156 (C4 (Web Text))

Max Activating Token Index: 174

Text #12

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4641. Min Act: -0.0000

Data Index: 605748 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4638. Min Act: -0.0001

Data Index: 518822 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4491. Min Act: -0.0001

Data Index: 1019569 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4136. Min Act: -0.0001

Data Index: 108909 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4449. Min Act: -0.0000

Data Index: 434014 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.3959. Min Act: -0.0001

Data Index: 284516 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4484. Min Act: -0.0000

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.8501. Min Range: -0.8501

Max Act: 0.4139. Min Act: -0.0001

Data Index: 452927 (C4 (Web Text))

Max Activating Token Index: 836