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

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

Neuron 5114 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.6442. Min Act: -0.0000

Data Index: 728624 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.7543. Min Act: -0.0000

Data Index: 1067891 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.8659. Min Act: -0.0000

Data Index: 379702 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.5070. Min Act: -0.0000

Data Index: 709149 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.6289. Min Act: -0.0000

Data Index: 125288 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.0233. Min Act: -0.0000

Data Index: 493492 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.1436. Min Act: -0.0000

Data Index: 998661 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.1096. Min Act: -0.0000

Data Index: 229955 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.2089. Min Act: -0.0000

Data Index: 1266040 (C4 (Web Text))

Max Activating Token Index: 745

Text #9

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.1788. Min Act: -0.0000

Data Index: 1222862 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.0145. Min Act: -0.0000

Data Index: 1314777 (C4 (Web Text))

Max Activating Token Index: 120

Text #11

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9649. Min Act: -0.0000

Data Index: 559082 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9587. Min Act: -0.0000

Data Index: 136686 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9485. Min Act: -0.0000

Data Index: 433748 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9476. Min Act: -0.0000

Data Index: 341130 (C4 (Web Text))

Max Activating Token Index: 513

Text #15

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9717. Min Act: -0.0000

Data Index: 933416 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9364. Min Act: -0.0000

Data Index: 1227141 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9345. Min Act: -0.0000

Data Index: 152278 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 3.8659. Min Range: -3.8659

Max Act: 2.9210. Min Act: -0.0000

Data Index: 47021 (C4 (Web Text))

Max Activating Token Index: 729

Text #19

Max Range: 3.8659. Min Range: -3.8659

Max Act: 3.0357. Min Act: -0.0000

Data Index: 646381 (C4 (Web Text))

Max Activating Token Index: 888