Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 644 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0003

Data Index: 559361 (C4 (Web Text))

Max Activating Token Index: 639

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0740. Min Act: -0.0003

Data Index: 112953 (C4 (Web Text))

Max Activating Token Index: 153

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1257805 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0669. Min Act: -0.0003

Data Index: 955200 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0676. Min Act: -0.0003

Data Index: 65227 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0684. Min Act: -0.0003

Data Index: 147113 (C4 (Web Text))

Max Activating Token Index: 961

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0686. Min Act: -0.0003

Data Index: 84965 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0709. Min Act: -0.0003

Data Index: 583513 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0651. Min Act: -0.0003

Data Index: 439436 (C4 (Web Text))

Max Activating Token Index: 522

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0674. Min Act: -0.0003

Data Index: 1184663 (C4 (Web Text))

Max Activating Token Index: 115

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0686. Min Act: -0.0003

Data Index: 518803 (C4 (Web Text))

Max Activating Token Index: 805

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0671. Min Act: -0.0003

Data Index: 1103284 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0593. Min Act: -0.0003

Data Index: 198457 (C4 (Web Text))

Max Activating Token Index: 394

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0673. Min Act: -0.0003

Data Index: 57011 (C4 (Web Text))

Max Activating Token Index: 687

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0661. Min Act: -0.0003

Data Index: 30486 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0662. Min Act: -0.0003

Data Index: 1292182 (C4 (Web Text))

Max Activating Token Index: 814

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0633. Min Act: -0.0003

Data Index: 1179253 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0616. Min Act: -0.0003

Data Index: 1352458 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0612. Min Act: -0.0003

Data Index: 600281 (C4 (Web Text))

Max Activating Token Index: 533

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0641. Min Act: -0.0003

Data Index: 436901 (C4 (Web Text))

Max Activating Token Index: 227