Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1980 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1302683 (C4 (Web Text))

Max Activating Token Index: 285

Text #1

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0845. Min Act: -0.0002

Data Index: 136644 (C4 (Web Text))

Max Activating Token Index: 403

Text #2

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0878. Min Act: -0.0002

Data Index: 601225 (C4 (Web Text))

Max Activating Token Index: 380

Text #3

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1239816 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1349324 (C4 (Web Text))

Max Activating Token Index: 144

Text #5

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0863. Min Act: -0.0002

Data Index: 206160 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0795. Min Act: -0.0002

Data Index: 284788 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0685. Min Act: -0.0002

Data Index: 376007 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0748. Min Act: -0.0002

Data Index: 880438 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0811. Min Act: -0.0002

Data Index: 658531 (C4 (Web Text))

Max Activating Token Index: 738

Text #10

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0802. Min Act: -0.0002

Data Index: 100410 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0797. Min Act: -0.0002

Data Index: 343485 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0774. Min Act: -0.0002

Data Index: 21373 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0739. Min Act: -0.0001

Data Index: 367090 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0761. Min Act: -0.0002

Data Index: 152945 (C4 (Web Text))

Max Activating Token Index: 391

Text #15

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0782. Min Act: -0.0002

Data Index: 357787 (C4 (Web Text))

Max Activating Token Index: 550

Text #16

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1088606 (C4 (Web Text))

Max Activating Token Index: 43

Text #17

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0790. Min Act: -0.0002

Data Index: 469422 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0761. Min Act: -0.0002

Data Index: 1270691 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.0942. Min Range: -0.0942

Max Act: 0.0704. Min Act: -0.0002

Data Index: 26441 (C4 (Web Text))

Max Activating Token Index: 208