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

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

Neuron 3616 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: 0.0885. Min Range: -0.0885

Max Act: 0.0885. Min Act: -0.0001

Data Index: 662292 (C4 (Web Text))

Max Activating Token Index: 421

Text #1

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0863. Min Act: -0.0001

Data Index: 1635824 (Python Code)

Max Activating Token Index: 56

Text #2

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0825. Min Act: -0.0001

Data Index: 492379 (C4 (Web Text))

Max Activating Token Index: 966

Text #3

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0840. Min Act: -0.0001

Data Index: 1611963 (Python Code)

Max Activating Token Index: 806

Text #4

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0832. Min Act: -0.0001

Data Index: 458007 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1434690 (Python Code)

Max Activating Token Index: 88

Text #6

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0800. Min Act: -0.0001

Data Index: 973851 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0789. Min Act: -0.0001

Data Index: 240422 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0787. Min Act: -0.0001

Data Index: 538319 (C4 (Web Text))

Max Activating Token Index: 118

Text #9

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0768. Min Act: -0.0001

Data Index: 1630651 (Python Code)

Max Activating Token Index: 74

Text #10

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0768. Min Act: -0.0001

Data Index: 583216 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1601152 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0784. Min Act: -0.0001

Data Index: 1638726 (Python Code)

Max Activating Token Index: 397

Text #13

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0753. Min Act: -0.0001

Data Index: 687544 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0758. Min Act: -0.0001

Data Index: 238385 (C4 (Web Text))

Max Activating Token Index: 721

Text #15

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1472849 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0740. Min Act: -0.0001

Data Index: 910438 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0745. Min Act: -0.0001

Data Index: 892896 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1190495 (C4 (Web Text))

Max Activating Token Index: 492

Text #19

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0744. Min Act: -0.0001

Data Index: 832372 (C4 (Web Text))

Max Activating Token Index: 28