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

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

Neuron 824 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.4282. Min Act: -0.0000

Data Index: 1222619 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1138998 (C4 (Web Text))

Max Activating Token Index: 678

Text #2

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1351971 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3741. Min Act: -0.0000

Data Index: 900834 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2917. Min Act: -0.0000

Data Index: 523652 (C4 (Web Text))

Max Activating Token Index: 681

Text #5

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2657. Min Act: -0.0000

Data Index: 767140 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.3057. Min Act: -0.0000

Data Index: 1013522 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2726. Min Act: -0.0000

Data Index: 602785 (C4 (Web Text))

Max Activating Token Index: 963

Text #8

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2814. Min Act: -0.0000

Data Index: 404608 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2782. Min Act: -0.0000

Data Index: 402905 (C4 (Web Text))

Max Activating Token Index: 648

Text #10

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2658. Min Act: -0.0000

Data Index: 152773 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2625. Min Act: -0.0000

Data Index: 775432 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2605. Min Act: -0.0000

Data Index: 214819 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2661. Min Act: -0.0000

Data Index: 1338774 (C4 (Web Text))

Max Activating Token Index: 615

Text #14

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2479. Min Act: -0.0000

Data Index: 119867 (C4 (Web Text))

Max Activating Token Index: 389

Text #15

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2566. Min Act: -0.0000

Data Index: 750615 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2703. Min Act: -0.0000

Data Index: 808731 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2600. Min Act: -0.0000

Data Index: 104472 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2429. Min Act: -0.0000

Data Index: 5170 (C4 (Web Text))

Max Activating Token Index: 568

Text #19

Max Range: 0.4282. Min Range: -0.4282

Max Act: 0.2388. Min Act: -0.0000

Data Index: 1143257 (C4 (Web Text))

Max Activating Token Index: 753