Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4604 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1068. Min Act: -0.0001

Data Index: 468166 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1015. Min Act: -0.0001

Data Index: 642382 (C4 (Web Text))

Max Activating Token Index: 539

Text #2

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1163. Min Act: -0.0001

Data Index: 297032 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1288. Min Act: -0.0001

Data Index: 646475 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0986. Min Act: -0.0001

Data Index: 528743 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.1062. Min Act: -0.0001

Data Index: 968046 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0811. Min Act: -0.0001

Data Index: 330076 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0768. Min Act: -0.0001

Data Index: 862384 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1006932 (C4 (Web Text))

Max Activating Token Index: 265

Text #9

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0873. Min Act: -0.0001

Data Index: 300589 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0924. Min Act: -0.0001

Data Index: 573298 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0730. Min Act: -0.0001

Data Index: 48995 (C4 (Web Text))

Max Activating Token Index: 250

Text #12

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0781. Min Act: -0.0001

Data Index: 134128 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0741. Min Act: -0.0001

Data Index: 508390 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0662. Min Act: -0.0001

Data Index: 645071 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0811. Min Act: -0.0001

Data Index: 199820 (C4 (Web Text))

Max Activating Token Index: 900

Text #16

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0721. Min Act: -0.0001

Data Index: 1198253 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0693. Min Act: -0.0001

Data Index: 900854 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0737. Min Act: -0.0001

Data Index: 1083893 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.1288. Min Range: -0.1288

Max Act: 0.0697. Min Act: -0.0001

Data Index: 992075 (C4 (Web Text))

Max Activating Token Index: 893