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

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

Neuron 3555 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.7694. Min Act: -0.0001

Data Index: 1252959 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.7902. Min Act: -0.0001

Data Index: 110897 (C4 (Web Text))

Max Activating Token Index: 526

Text #2

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.6837. Min Act: -0.0001

Data Index: 705660 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.6592. Min Act: -0.0002

Data Index: 75468 (C4 (Web Text))

Max Activating Token Index: 381

Text #4

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1050606 (C4 (Web Text))

Max Activating Token Index: 102

Text #5

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5858. Min Act: -0.0001

Data Index: 953604 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5581. Min Act: -0.0001

Data Index: 873293 (C4 (Web Text))

Max Activating Token Index: 480

Text #7

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5925. Min Act: -0.0001

Data Index: 728434 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5650. Min Act: -0.0001

Data Index: 1058518 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5951. Min Act: -0.0001

Data Index: 1297744 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5769. Min Act: -0.0001

Data Index: 156789 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5527. Min Act: -0.0001

Data Index: 837914 (C4 (Web Text))

Max Activating Token Index: 96

Text #12

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.4490. Min Act: -0.0001

Data Index: 616845 (C4 (Web Text))

Max Activating Token Index: 1016

Text #13

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5807. Min Act: -0.0001

Data Index: 993181 (C4 (Web Text))

Max Activating Token Index: 453

Text #14

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5245. Min Act: -0.0001

Data Index: 366897 (C4 (Web Text))

Max Activating Token Index: 722

Text #15

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5242. Min Act: -0.0001

Data Index: 636926 (C4 (Web Text))

Max Activating Token Index: 880

Text #16

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5223. Min Act: -0.0001

Data Index: 442434 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5050. Min Act: -0.0001

Data Index: 31490 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5604. Min Act: -0.0001

Data Index: 1298209 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.7902. Min Range: -0.7902

Max Act: 0.5441. Min Act: -0.0001

Data Index: 977063 (C4 (Web Text))

Max Activating Token Index: 360