Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1388 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0936. Min Act: -0.0002

Data Index: 678192 (C4 (Web Text))

Max Activating Token Index: 394

Text #1

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0916. Min Act: -0.0002

Data Index: 987961 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0786. Min Act: -0.0002

Data Index: 675619 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1154485 (C4 (Web Text))

Max Activating Token Index: 368

Text #4

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1282772 (C4 (Web Text))

Max Activating Token Index: 876

Text #5

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0745. Min Act: -0.0001

Data Index: 1080124 (C4 (Web Text))

Max Activating Token Index: 835

Text #6

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0668. Min Act: -0.0001

Data Index: 179695 (C4 (Web Text))

Max Activating Token Index: 375

Text #7

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0724. Min Act: -0.0001

Data Index: 193723 (C4 (Web Text))

Max Activating Token Index: 887

Text #8

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0697. Min Act: -0.0001

Data Index: 783241 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0714. Min Act: -0.0001

Data Index: 335402 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0707. Min Act: -0.0002

Data Index: 705123 (C4 (Web Text))

Max Activating Token Index: 524

Text #11

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0685. Min Act: -0.0002

Data Index: 133404 (C4 (Web Text))

Max Activating Token Index: 996

Text #12

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0693. Min Act: -0.0002

Data Index: 432069 (C4 (Web Text))

Max Activating Token Index: 128

Text #13

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0718. Min Act: -0.0001

Data Index: 747257 (C4 (Web Text))

Max Activating Token Index: 458

Text #14

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0666. Min Act: -0.0002

Data Index: 10601 (C4 (Web Text))

Max Activating Token Index: 192

Text #15

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0693. Min Act: -0.0002

Data Index: 533036 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0719. Min Act: -0.0001

Data Index: 698086 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0660. Min Act: -0.0002

Data Index: 41167 (C4 (Web Text))

Max Activating Token Index: 926

Text #18

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0657. Min Act: -0.0001

Data Index: 557459 (C4 (Web Text))

Max Activating Token Index: 714

Text #19

Max Range: 0.0936. Min Range: -0.0936

Max Act: 0.0680. Min Act: -0.0001

Data Index: 502983 (C4 (Web Text))

Max Activating Token Index: 914