Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 319 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.7690. Min Act: -0.0002

Data Index: 1001447 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6629. Min Act: -0.0001

Data Index: 23187 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6464. Min Act: -0.0002

Data Index: 893161 (C4 (Web Text))

Max Activating Token Index: 692

Text #3

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.6161. Min Act: -0.0001

Data Index: 1208325 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5966. Min Act: -0.0001

Data Index: 700490 (C4 (Web Text))

Max Activating Token Index: 677

Text #5

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5691. Min Act: -0.0001

Data Index: 1353242 (C4 (Web Text))

Max Activating Token Index: 22

Text #6

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5864. Min Act: -0.0001

Data Index: 214965 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5644. Min Act: -0.0001

Data Index: 33131 (C4 (Web Text))

Max Activating Token Index: 772

Text #8

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5671. Min Act: -0.0002

Data Index: 406417 (C4 (Web Text))

Max Activating Token Index: 18

Text #9

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5588. Min Act: -0.0001

Data Index: 919009 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5191. Min Act: -0.0002

Data Index: 180350 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5790. Min Act: -0.0002

Data Index: 798950 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5737. Min Act: -0.0001

Data Index: 558472 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5871. Min Act: -0.0001

Data Index: 264667 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5722. Min Act: -0.0001

Data Index: 1085546 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5627. Min Act: -0.0002

Data Index: 59685 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5451. Min Act: -0.0002

Data Index: 513728 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5763. Min Act: -0.0002

Data Index: 1289488 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5784. Min Act: -0.0001

Data Index: 249698 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.7690. Min Range: -0.7690

Max Act: 0.5357. Min Act: -0.0002

Data Index: 1278419 (C4 (Web Text))

Max Activating Token Index: 379