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

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

Neuron 5456 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: 0.9642. Min Range: -0.9642

Max Act: 0.9642. Min Act: -0.0002

Data Index: 1085710 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.9392. Min Act: -0.0002

Data Index: 854123 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.9037. Min Act: -0.0002

Data Index: 998257 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8947. Min Act: -0.0002

Data Index: 804992 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8871. Min Act: -0.0002

Data Index: 547264 (C4 (Web Text))

Max Activating Token Index: 464

Text #5

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8811. Min Act: -0.0002

Data Index: 24452 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8645. Min Act: -0.0002

Data Index: 345272 (C4 (Web Text))

Max Activating Token Index: 938

Text #7

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8182. Min Act: -0.0002

Data Index: 540727 (C4 (Web Text))

Max Activating Token Index: 631

Text #8

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8267. Min Act: -0.0002

Data Index: 586990 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8251. Min Act: -0.0002

Data Index: 72904 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8063. Min Act: -0.0002

Data Index: 281819 (C4 (Web Text))

Max Activating Token Index: 852

Text #11

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.8111. Min Act: -0.0002

Data Index: 1308037 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7979. Min Act: -0.0002

Data Index: 1171300 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7783. Min Act: -0.0002

Data Index: 1009736 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7825. Min Act: -0.0002

Data Index: 418741 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7602. Min Act: -0.0002

Data Index: 1058688 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7652. Min Act: -0.0002

Data Index: 511508 (C4 (Web Text))

Max Activating Token Index: 305

Text #17

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7653. Min Act: -0.0002

Data Index: 966393 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7417. Min Act: -0.0002

Data Index: 643249 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.9642. Min Range: -0.9642

Max Act: 0.7377. Min Act: -0.0002

Data Index: 1111606 (C4 (Web Text))

Max Activating Token Index: 934