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

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

Neuron 1104 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0506. Min Range: -1.0506

Max Act: 1.0506. Min Act: -0.0000

Data Index: 455386 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.9032. Min Act: -0.0000

Data Index: 653476 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8899. Min Act: -0.0000

Data Index: 369518 (C4 (Web Text))

Max Activating Token Index: 681

Text #3

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1216076 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8037. Min Act: -0.0000

Data Index: 122057 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8783. Min Act: -0.0000

Data Index: 935750 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8275. Min Act: -0.0000

Data Index: 355426 (C4 (Web Text))

Max Activating Token Index: 974

Text #7

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8281. Min Act: 0.0000

Data Index: 766637 (C4 (Web Text))

Max Activating Token Index: 259

Text #8

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8145. Min Act: -0.0000

Data Index: 265324 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8122. Min Act: -0.0000

Data Index: 719739 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.8092. Min Act: -0.0000

Data Index: 423088 (C4 (Web Text))

Max Activating Token Index: 433

Text #11

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1029094 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1280826 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7984. Min Act: -0.0000

Data Index: 420187 (C4 (Web Text))

Max Activating Token Index: 943

Text #14

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7831. Min Act: -0.0000

Data Index: 808892 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7277. Min Act: -0.0000

Data Index: 408672 (C4 (Web Text))

Max Activating Token Index: 129

Text #16

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7657. Min Act: -0.0000

Data Index: 676615 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7430. Min Act: -0.0000

Data Index: 1050134 (C4 (Web Text))

Max Activating Token Index: 300

Text #18

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7634. Min Act: -0.0000

Data Index: 714948 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 1.0506. Min Range: -1.0506

Max Act: 0.7632. Min Act: -0.0000

Data Index: 561100 (C4 (Web Text))

Max Activating Token Index: 520