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

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

Neuron 1626 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0713. Min Range: -1.0713

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1286453 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.9387. Min Act: -0.0000

Data Index: 956008 (C4 (Web Text))

Max Activating Token Index: 589

Text #2

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.9850. Min Act: -0.0000

Data Index: 822366 (C4 (Web Text))

Max Activating Token Index: 717

Text #3

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8885. Min Act: -0.0000

Data Index: 1110593 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8563. Min Act: -0.0000

Data Index: 713132 (C4 (Web Text))

Max Activating Token Index: 534

Text #5

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8639. Min Act: -0.0000

Data Index: 1266606 (C4 (Web Text))

Max Activating Token Index: 239

Text #6

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8116. Min Act: -0.0000

Data Index: 428907 (C4 (Web Text))

Max Activating Token Index: 136

Text #7

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1074522 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8568. Min Act: -0.0000

Data Index: 248858 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8828. Min Act: -0.0000

Data Index: 993711 (C4 (Web Text))

Max Activating Token Index: 516

Text #10

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8149. Min Act: -0.0000

Data Index: 1195359 (C4 (Web Text))

Max Activating Token Index: 511

Text #11

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8131. Min Act: -0.0000

Data Index: 927050 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.7330. Min Act: -0.0000

Data Index: 644420 (C4 (Web Text))

Max Activating Token Index: 307

Text #13

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8008. Min Act: -0.0000

Data Index: 1312673 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.8166. Min Act: -0.0000

Data Index: 897967 (C4 (Web Text))

Max Activating Token Index: 576

Text #15

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.7855. Min Act: -0.0000

Data Index: 115369 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.7838. Min Act: -0.0000

Data Index: 673256 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.7524. Min Act: -0.0000

Data Index: 234897 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.7499. Min Act: -0.0000

Data Index: 1307581 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 1.0713. Min Range: -1.0713

Max Act: 0.7280. Min Act: -0.0000

Data Index: 34527 (C4 (Web Text))

Max Activating Token Index: 657