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

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

Neuron 6099 in Layer 1

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: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0002

Data Index: 269460 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0643. Min Act: -0.0002

Data Index: 283260 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0618. Min Act: -0.0002

Data Index: 306773 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0603. Min Act: -0.0003

Data Index: 124411 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0590. Min Act: -0.0002

Data Index: 340649 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0564. Min Act: -0.0002

Data Index: 911542 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0560. Min Act: -0.0003

Data Index: 883241 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0560. Min Act: -0.0002

Data Index: 379163 (C4 (Web Text))

Max Activating Token Index: 726

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0554. Min Act: -0.0003

Data Index: 1294680 (C4 (Web Text))

Max Activating Token Index: 722

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0544. Min Act: -0.0002

Data Index: 13620 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0534. Min Act: -0.0002

Data Index: 1099672 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1342631 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1040732 (C4 (Web Text))

Max Activating Token Index: 153

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0489. Min Act: -0.0002

Data Index: 581067 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0491. Min Act: -0.0002

Data Index: 310184 (C4 (Web Text))

Max Activating Token Index: 642

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0479. Min Act: -0.0002

Data Index: 946574 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1127420 (C4 (Web Text))

Max Activating Token Index: 179

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0475. Min Act: -0.0002

Data Index: 1058383 (C4 (Web Text))

Max Activating Token Index: 892

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0469. Min Act: -0.0002

Data Index: 807268 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0472. Min Act: -0.0002

Data Index: 65810 (C4 (Web Text))

Max Activating Token Index: 586