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

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

Neuron 2030 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1340853 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 643987 (C4 (Web Text))

Max Activating Token Index: 921

Text #2

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 868173 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 569264 (C4 (Web Text))

Max Activating Token Index: 906

Text #4

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1020075 (C4 (Web Text))

Max Activating Token Index: 971

Text #5

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1138760 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1063531 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 510578 (C4 (Web Text))

Max Activating Token Index: 916

Text #8

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 624386 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 949113 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 544751 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 259239 (C4 (Web Text))

Max Activating Token Index: 553

Text #12

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 548098 (C4 (Web Text))

Max Activating Token Index: 926

Text #13

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1282604 (C4 (Web Text))

Max Activating Token Index: 617

Text #14

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 482167 (C4 (Web Text))

Max Activating Token Index: 910

Text #15

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1201457 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 334649 (C4 (Web Text))

Max Activating Token Index: 944

Text #17

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 635319 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 226687 (C4 (Web Text))

Max Activating Token Index: 914

Text #19

Max Range: 0.0003. Min Range: -0.0003

Max Act: 0.0003. Min Act: -0.0001

Data Index: 458413 (C4 (Web Text))

Max Activating Token Index: 689