Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 124 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0921. Min Act: -0.0003

Data Index: 643060 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0889. Min Act: -0.0003

Data Index: 500376 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0877. Min Act: -0.0003

Data Index: 644435 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0822. Min Act: -0.0003

Data Index: 227311 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0805. Min Act: -0.0002

Data Index: 442632 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0787. Min Act: -0.0003

Data Index: 529800 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0783. Min Act: -0.0003

Data Index: 108434 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0736. Min Act: -0.0002

Data Index: 482940 (C4 (Web Text))

Max Activating Token Index: 382

Text #8

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0775. Min Act: -0.0003

Data Index: 354845 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0756. Min Act: -0.0003

Data Index: 245289 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0764. Min Act: -0.0003

Data Index: 368264 (C4 (Web Text))

Max Activating Token Index: 158

Text #11

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0755. Min Act: -0.0003

Data Index: 111975 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0742. Min Act: -0.0003

Data Index: 1276324 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0730. Min Act: -0.0003

Data Index: 879349 (C4 (Web Text))

Max Activating Token Index: 370

Text #14

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0753. Min Act: -0.0003

Data Index: 1108113 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0694. Min Act: -0.0002

Data Index: 620413 (C4 (Web Text))

Max Activating Token Index: 958

Text #16

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0718. Min Act: -0.0001

Data Index: 882584 (C4 (Web Text))

Max Activating Token Index: 646

Text #17

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0713. Min Act: -0.0003

Data Index: 1332084 (C4 (Web Text))

Max Activating Token Index: 338

Text #18

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1278726 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.0921. Min Range: -0.0921

Max Act: 0.0710. Min Act: -0.0003

Data Index: 991941 (C4 (Web Text))

Max Activating Token Index: 120