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

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

Neuron 1921 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: 0.7482. Min Range: -0.7482

Max Act: 0.7482. Min Act: -0.0000

Data Index: 809908 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.5475. Min Act: -0.0000

Data Index: 658171 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.5169. Min Act: -0.0000

Data Index: 283355 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1065364 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4898. Min Act: -0.0000

Data Index: 869413 (C4 (Web Text))

Max Activating Token Index: 901

Text #5

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.5066. Min Act: -0.0000

Data Index: 164967 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4691. Min Act: -0.0000

Data Index: 459602 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.5144. Min Act: -0.0000

Data Index: 368835 (C4 (Web Text))

Max Activating Token Index: 39

Text #8

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4624. Min Act: -0.0000

Data Index: 682639 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4467. Min Act: -0.0000

Data Index: 175767 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4828. Min Act: -0.0000

Data Index: 1172743 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4338. Min Act: -0.0000

Data Index: 353976 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1215582 (C4 (Web Text))

Max Activating Token Index: 591

Text #13

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4433. Min Act: -0.0000

Data Index: 524715 (C4 (Web Text))

Max Activating Token Index: 815

Text #14

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4588. Min Act: -0.0000

Data Index: 31047 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4204. Min Act: -0.0000

Data Index: 663601 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4068. Min Act: -0.0000

Data Index: 529824 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4226. Min Act: -0.0000

Data Index: 692571 (C4 (Web Text))

Max Activating Token Index: 313

Text #18

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4350. Min Act: -0.0000

Data Index: 975033 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 0.7482. Min Range: -0.7482

Max Act: 0.4544. Min Act: -0.0000

Data Index: 1299105 (C4 (Web Text))

Max Activating Token Index: 610