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

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

Neuron 456 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: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0001

Data Index: 985703 (C4 (Web Text))

Max Activating Token Index: 931

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0739. Min Act: -0.0001

Data Index: 1259756 (C4 (Web Text))

Max Activating Token Index: 6

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1275659 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0709. Min Act: -0.0001

Data Index: 875102 (C4 (Web Text))

Max Activating Token Index: 888

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0695. Min Act: -0.0001

Data Index: 233543 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0666. Min Act: -0.0001

Data Index: 595195 (C4 (Web Text))

Max Activating Token Index: 729

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0653. Min Act: -0.0001

Data Index: 131616 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0650. Min Act: -0.0001

Data Index: 688982 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1169687 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1048139 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0620. Min Act: -0.0001

Data Index: 339615 (C4 (Web Text))

Max Activating Token Index: 651

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0605. Min Act: -0.0001

Data Index: 460883 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0622. Min Act: -0.0002

Data Index: 145436 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0618. Min Act: -0.0001

Data Index: 1152697 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0610. Min Act: -0.0001

Data Index: 1211337 (C4 (Web Text))

Max Activating Token Index: 577

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0627. Min Act: -0.0001

Data Index: 232196 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0598. Min Act: -0.0001

Data Index: 1236397 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0607. Min Act: -0.0001

Data Index: 544488 (C4 (Web Text))

Max Activating Token Index: 947

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0607. Min Act: -0.0001

Data Index: 998042 (C4 (Web Text))

Max Activating Token Index: 923

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0593. Min Act: -0.0001

Data Index: 1196321 (C4 (Web Text))

Max Activating Token Index: 21