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

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

Neuron 1744 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3049. Min Range: -2.3049

Max Act: 2.1469. Min Act: 0.0000

Data Index: 531965 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 2.3049. Min Range: -2.3049

Max Act: 2.3049. Min Act: -0.0000

Data Index: 524889 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.7405. Min Act: -0.0000

Data Index: 475968 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 2.3049. Min Range: -2.3049

Max Act: 2.0314. Min Act: -0.0000

Data Index: 958805 (C4 (Web Text))

Max Activating Token Index: 75

Text #4

Max Range: 2.3049. Min Range: -2.3049

Max Act: 2.2105. Min Act: -0.0000

Data Index: 614070 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.8934. Min Act: -0.0000

Data Index: 23306 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 2.3049. Min Range: -2.3049

Max Act: 2.1155. Min Act: -0.0000

Data Index: 435319 (C4 (Web Text))

Max Activating Token Index: 946

Text #7

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.9261. Min Act: -0.0000

Data Index: 1209442 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 2.3049. Min Range: -2.3049

Max Act: 2.0300. Min Act: -0.0000

Data Index: 643161 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.9893. Min Act: -0.0000

Data Index: 413548 (C4 (Web Text))

Max Activating Token Index: 418

Text #10

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.9736. Min Act: -0.0000

Data Index: 1328708 (C4 (Web Text))

Max Activating Token Index: 427

Text #11

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.8682. Min Act: -0.0000

Data Index: 296965 (C4 (Web Text))

Max Activating Token Index: 470

Text #12

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.8470. Min Act: -0.0000

Data Index: 271638 (C4 (Web Text))

Max Activating Token Index: 599

Text #13

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.8262. Min Act: -0.0000

Data Index: 1341349 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.7035. Min Act: -0.0000

Data Index: 684199 (C4 (Web Text))

Max Activating Token Index: 793

Text #15

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.8749. Min Act: 0.0000

Data Index: 218329 (C4 (Web Text))

Max Activating Token Index: 701

Text #16

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.7753. Min Act: -0.0000

Data Index: 558033 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.9301. Min Act: -0.0000

Data Index: 242695 (C4 (Web Text))

Max Activating Token Index: 324

Text #18

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.7251. Min Act: -0.0000

Data Index: 960598 (C4 (Web Text))

Max Activating Token Index: 908

Text #19

Max Range: 2.3049. Min Range: -2.3049

Max Act: 1.6751. Min Act: 0.0000

Data Index: 562359 (C4 (Web Text))

Max Activating Token Index: 87