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

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

Neuron 2491 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: 0.0863. Min Range: -0.0863

Max Act: 0.0863. Min Act: -0.0002

Data Index: 906040 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1290679 (C4 (Web Text))

Max Activating Token Index: 84

Text #2

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0777. Min Act: -0.0002

Data Index: 487350 (C4 (Web Text))

Max Activating Token Index: 165

Text #3

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0782. Min Act: -0.0002

Data Index: 997842 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0776. Min Act: -0.0002

Data Index: 741103 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1063991 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0742. Min Act: -0.0002

Data Index: 996791 (C4 (Web Text))

Max Activating Token Index: 144

Text #7

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0760. Min Act: -0.0002

Data Index: 86467 (C4 (Web Text))

Max Activating Token Index: 841

Text #8

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0749. Min Act: -0.0002

Data Index: 656389 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0718. Min Act: -0.0002

Data Index: 881791 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1099209 (C4 (Web Text))

Max Activating Token Index: 345

Text #11

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1072698 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0690. Min Act: -0.0002

Data Index: 588061 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0711. Min Act: -0.0002

Data Index: 971244 (C4 (Web Text))

Max Activating Token Index: 495

Text #14

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1121515 (C4 (Web Text))

Max Activating Token Index: 193

Text #15

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0689. Min Act: -0.0002

Data Index: 1250008 (C4 (Web Text))

Max Activating Token Index: 348

Text #16

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0690. Min Act: -0.0002

Data Index: 819671 (C4 (Web Text))

Max Activating Token Index: 238

Text #17

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0692. Min Act: -0.0002

Data Index: 972034 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0683. Min Act: -0.0002

Data Index: 670462 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0669. Min Act: -0.0002

Data Index: 1043980 (C4 (Web Text))

Max Activating Token Index: 393