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

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

Neuron 850 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.4783. Min Act: -0.0000

Data Index: 350594 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.3243. Min Act: -0.0000

Data Index: 428633 (C4 (Web Text))

Max Activating Token Index: 571

Text #2

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.2376. Min Act: -0.0000

Data Index: 309830 (C4 (Web Text))

Max Activating Token Index: 847

Text #3

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.3076. Min Act: -0.0000

Data Index: 453087 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.2878. Min Act: -0.0000

Data Index: 1120623 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1203. Min Act: -0.0000

Data Index: 431696 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1257. Min Act: -0.0000

Data Index: 781393 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1212. Min Act: -0.0000

Data Index: 130016 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0808. Min Act: -0.0000

Data Index: 1126115 (C4 (Web Text))

Max Activating Token Index: 186

Text #9

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1377. Min Act: -0.0000

Data Index: 38925 (C4 (Web Text))

Max Activating Token Index: 900

Text #10

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9810. Min Act: -0.0000

Data Index: 914916 (C4 (Web Text))

Max Activating Token Index: 156

Text #11

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0766. Min Act: -0.0000

Data Index: 90241 (C4 (Web Text))

Max Activating Token Index: 395

Text #12

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0308. Min Act: -0.0000

Data Index: 806061 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.1891. Min Act: -0.0000

Data Index: 974392 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9948. Min Act: -0.0000

Data Index: 62692 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 1.4783. Min Range: -1.4783

Max Act: 1.0308. Min Act: -0.0000

Data Index: 656156 (C4 (Web Text))

Max Activating Token Index: 941

Text #16

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9795. Min Act: -0.0000

Data Index: 807439 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9782. Min Act: -0.0000

Data Index: 752971 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9790. Min Act: -0.0000

Data Index: 41866 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.4783. Min Range: -1.4783

Max Act: 0.9257. Min Act: -0.0000

Data Index: 1326363 (C4 (Web Text))

Max Activating Token Index: 642