Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1815 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0771. Min Act: -0.0003

Data Index: 280683 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0770. Min Act: -0.0003

Data Index: 1189925 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0744. Min Act: -0.0003

Data Index: 435421 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0784. Min Act: -0.0003

Data Index: 416782 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1266163 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0667. Min Act: -0.0003

Data Index: 166468 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0708. Min Act: -0.0003

Data Index: 706460 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0699. Min Act: -0.0003

Data Index: 774004 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1162785 (C4 (Web Text))

Max Activating Token Index: 641

Text #9

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0672. Min Act: -0.0003

Data Index: 898158 (C4 (Web Text))

Max Activating Token Index: 318

Text #10

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0660. Min Act: -0.0003

Data Index: 1298837 (C4 (Web Text))

Max Activating Token Index: 849

Text #11

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0688. Min Act: -0.0003

Data Index: 1179410 (C4 (Web Text))

Max Activating Token Index: 136

Text #12

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0660. Min Act: -0.0003

Data Index: 686664 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0687. Min Act: -0.0003

Data Index: 636638 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0626. Min Act: -0.0003

Data Index: 1267040 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0701. Min Act: -0.0003

Data Index: 572512 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0620. Min Act: -0.0003

Data Index: 689071 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0649. Min Act: -0.0003

Data Index: 919959 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0744. Min Act: -0.0003

Data Index: 1045556 (C4 (Web Text))

Max Activating Token Index: 622

Text #19

Max Range: 0.0784. Min Range: -0.0784

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1026621 (C4 (Web Text))

Max Activating Token Index: 784