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

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

Neuron 5914 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: 0.5893. Min Range: -0.5893

Max Act: 0.5893. Min Act: -0.0001

Data Index: 543078 (C4 (Web Text))

Max Activating Token Index: 273

Text #1

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5750. Min Act: -0.0001

Data Index: 1229835 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5711. Min Act: -0.0001

Data Index: 1080164 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5645. Min Act: -0.0001

Data Index: 1123841 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5629. Min Act: -0.0001

Data Index: 1296712 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5707. Min Act: -0.0001

Data Index: 96311 (C4 (Web Text))

Max Activating Token Index: 29

Text #6

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5664. Min Act: -0.0001

Data Index: 937916 (C4 (Web Text))

Max Activating Token Index: 125

Text #7

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5509. Min Act: -0.0001

Data Index: 488295 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5622. Min Act: -0.0001

Data Index: 1125413 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5443. Min Act: -0.0002

Data Index: 835687 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5586. Min Act: -0.0001

Data Index: 20658 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5597. Min Act: -0.0001

Data Index: 1095900 (C4 (Web Text))

Max Activating Token Index: 321

Text #12

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5532. Min Act: -0.0001

Data Index: 439831 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5514. Min Act: -0.0001

Data Index: 1350062 (C4 (Web Text))

Max Activating Token Index: 783

Text #14

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5453. Min Act: -0.0001

Data Index: 982601 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5450. Min Act: -0.0001

Data Index: 260620 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5388. Min Act: -0.0001

Data Index: 623785 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5387. Min Act: -0.0001

Data Index: 1216917 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5390. Min Act: -0.0001

Data Index: 375391 (C4 (Web Text))

Max Activating Token Index: 152

Text #19

Max Range: 0.5893. Min Range: -0.5893

Max Act: 0.5354. Min Act: -0.0001

Data Index: 826243 (C4 (Web Text))

Max Activating Token Index: 125