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

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

Neuron 2107 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: 0.6103. Min Range: -0.6103

Max Act: 0.6102. Min Act: -0.0001

Data Index: 91602 (C4 (Web Text))

Max Activating Token Index: 205

Text #1

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.6078. Min Act: -0.0001

Data Index: 246237 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.6103. Min Act: -0.0001

Data Index: 25515 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5940. Min Act: -0.0001

Data Index: 625484 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5894. Min Act: -0.0001

Data Index: 568898 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5921. Min Act: -0.0001

Data Index: 971334 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5793. Min Act: -0.0001

Data Index: 929673 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5858. Min Act: -0.0001

Data Index: 564049 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5912. Min Act: -0.0001

Data Index: 254507 (C4 (Web Text))

Max Activating Token Index: 358

Text #9

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5800. Min Act: -0.0001

Data Index: 685467 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5677. Min Act: -0.0001

Data Index: 766996 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5797. Min Act: -0.0001

Data Index: 1293738 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5806. Min Act: -0.0001

Data Index: 738684 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5717. Min Act: -0.0001

Data Index: 579609 (C4 (Web Text))

Max Activating Token Index: 368

Text #14

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5673. Min Act: -0.0001

Data Index: 509922 (C4 (Web Text))

Max Activating Token Index: 27

Text #15

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5637. Min Act: -0.0001

Data Index: 96541 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5732. Min Act: -0.0001

Data Index: 1365 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5593. Min Act: -0.0001

Data Index: 189580 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5566. Min Act: -0.0001

Data Index: 1102882 (C4 (Web Text))

Max Activating Token Index: 77

Text #19

Max Range: 0.6103. Min Range: -0.6103

Max Act: 0.5568. Min Act: -0.0001

Data Index: 582095 (C4 (Web Text))

Max Activating Token Index: 418