Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 106 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: -0.0001

Data Index: 1563003 (Python Code)

Max Activating Token Index: 467

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0870. Min Act: -0.0001

Data Index: 384807 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1091268 (C4 (Web Text))

Max Activating Token Index: 780

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0778. Min Act: -0.0001

Data Index: 911735 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0827. Min Act: -0.0001

Data Index: 662469 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0836. Min Act: -0.0001

Data Index: 652858 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0710. Min Act: -0.0001

Data Index: 262716 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0654. Min Act: -0.0001

Data Index: 830833 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0774. Min Act: -0.0001

Data Index: 435498 (C4 (Web Text))

Max Activating Token Index: 958

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0778. Min Act: -0.0001

Data Index: 771497 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0650. Min Act: -0.0001

Data Index: 1058035 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0717. Min Act: -0.0001

Data Index: 1077747 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0727. Min Act: -0.0001

Data Index: 717639 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0696. Min Act: -0.0001

Data Index: 1158820 (C4 (Web Text))

Max Activating Token Index: 620

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0724. Min Act: -0.0001

Data Index: 1333708 (C4 (Web Text))

Max Activating Token Index: 562

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0716. Min Act: -0.0001

Data Index: 425059 (C4 (Web Text))

Max Activating Token Index: 2

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0763. Min Act: -0.0001

Data Index: 987259 (C4 (Web Text))

Max Activating Token Index: 883

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1225320 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0704. Min Act: -0.0001

Data Index: 573421 (C4 (Web Text))

Max Activating Token Index: 1020

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0677. Min Act: -0.0001

Data Index: 1325346 (C4 (Web Text))

Max Activating Token Index: 543