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

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

Neuron 3888 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: 2.2919. Min Range: -2.2919

Max Act: 2.2919. Min Act: -0.0000

Data Index: 459338 (C4 (Web Text))

Max Activating Token Index: 724

Text #1

Max Range: 2.2919. Min Range: -2.2919

Max Act: 2.0073. Min Act: -0.0000

Data Index: 1488453 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.8682. Min Act: -0.0000

Data Index: 22367 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6699. Min Act: -0.0000

Data Index: 1506718 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6964. Min Act: -0.0000

Data Index: 852369 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6602. Min Act: -0.0000

Data Index: 577298 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6634. Min Act: -0.0000

Data Index: 915011 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6756. Min Act: -0.0000

Data Index: 1147088 (C4 (Web Text))

Max Activating Token Index: 515

Text #8

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1175010 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5582. Min Act: -0.0000

Data Index: 1529114 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5908. Min Act: -0.0000

Data Index: 359821 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6609. Min Act: -0.0000

Data Index: 354069 (C4 (Web Text))

Max Activating Token Index: 177

Text #12

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1007859 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6477. Min Act: -0.0000

Data Index: 629063 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5715. Min Act: -0.0000

Data Index: 397260 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6073. Min Act: -0.0000

Data Index: 1020371 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5646. Min Act: -0.0000

Data Index: 1046121 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5616. Min Act: -0.0000

Data Index: 1219528 (C4 (Web Text))

Max Activating Token Index: 645

Text #18

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.6500. Min Act: -0.0000

Data Index: 724890 (C4 (Web Text))

Max Activating Token Index: 192

Text #19

Max Range: 2.2919. Min Range: -2.2919

Max Act: 1.5603. Min Act: -0.0000

Data Index: 1239189 (C4 (Web Text))

Max Activating Token Index: 850