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

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

Neuron 3964 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.4309. Min Act: -0.0000

Data Index: 970091 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3487. Min Act: -0.0001

Data Index: 461277 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3354. Min Act: -0.0001

Data Index: 392611 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3328. Min Act: -0.0001

Data Index: 486949 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3168. Min Act: -0.0000

Data Index: 3959 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3059. Min Act: -0.0001

Data Index: 1134919 (C4 (Web Text))

Max Activating Token Index: 166

Text #6

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3145. Min Act: -0.0001

Data Index: 1067247 (C4 (Web Text))

Max Activating Token Index: 271

Text #7

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1242087 (C4 (Web Text))

Max Activating Token Index: 710

Text #8

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.3094. Min Act: -0.0001

Data Index: 585031 (C4 (Web Text))

Max Activating Token Index: 506

Text #9

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2894. Min Act: -0.0001

Data Index: 648461 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2972. Min Act: -0.0000

Data Index: 1260522 (C4 (Web Text))

Max Activating Token Index: 18

Text #11

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2935. Min Act: -0.0001

Data Index: 1282012 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2931. Min Act: -0.0001

Data Index: 336770 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2822. Min Act: -0.0000

Data Index: 429459 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2889. Min Act: -0.0000

Data Index: 1137336 (C4 (Web Text))

Max Activating Token Index: 22

Text #15

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2789. Min Act: -0.0001

Data Index: 1043506 (C4 (Web Text))

Max Activating Token Index: 519

Text #16

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2635. Min Act: -0.0001

Data Index: 286043 (C4 (Web Text))

Max Activating Token Index: 104

Text #17

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2813. Min Act: -0.0001

Data Index: 407082 (C4 (Web Text))

Max Activating Token Index: 14

Text #18

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2905. Min Act: -0.0001

Data Index: 1221994 (C4 (Web Text))

Max Activating Token Index: 765

Text #19

Max Range: 0.4309. Min Range: -0.4309

Max Act: 0.2687. Min Act: -0.0000

Data Index: 1299742 (C4 (Web Text))

Max Activating Token Index: 853