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

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

Neuron 4668 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1091. Min Range: -5.1091

Max Act: 5.1091. Min Act: -0.0001

Data Index: 13472 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 5.1091. Min Range: -5.1091

Max Act: 4.2840. Min Act: -0.0001

Data Index: 309749 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 5.1091. Min Range: -5.1091

Max Act: 3.9804. Min Act: -0.0000

Data Index: 968981 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 5.1091. Min Range: -5.1091

Max Act: 3.9208. Min Act: -0.0001

Data Index: 920938 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 5.1091. Min Range: -5.1091

Max Act: 4.0564. Min Act: -0.0001

Data Index: 333862 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 5.1091. Min Range: -5.1091

Max Act: 3.9117. Min Act: -0.0001

Data Index: 789056 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 5.1091. Min Range: -5.1091

Max Act: 3.7256. Min Act: -0.0001

Data Index: 1110328 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 5.1091. Min Range: -5.1091

Max Act: 3.8831. Min Act: -0.0000

Data Index: 1330970 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.9462. Min Act: -0.0001

Data Index: 466895 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.9846. Min Act: -0.0000

Data Index: 534125 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.8914. Min Act: -0.0001

Data Index: 15203 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.2633. Min Act: -0.0001

Data Index: 556891 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.7492. Min Act: -0.0000

Data Index: 1086935 (C4 (Web Text))

Max Activating Token Index: 191

Text #13

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.7330. Min Act: -0.0001

Data Index: 175313 (C4 (Web Text))

Max Activating Token Index: 988

Text #14

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.8203. Min Act: -0.0001

Data Index: 293697 (C4 (Web Text))

Max Activating Token Index: 515

Text #15

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.8223. Min Act: -0.0000

Data Index: 300241 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.8033. Min Act: -0.0000

Data Index: 847010 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.6581. Min Act: -0.0000

Data Index: 372877 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.2852. Min Act: -0.0001

Data Index: 237456 (C4 (Web Text))

Max Activating Token Index: 939

Text #19

Max Range: 5.1091. Min Range: -5.1091

Max Act: 2.6311. Min Act: -0.0001

Data Index: 868560 (C4 (Web Text))

Max Activating Token Index: 28