Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 227 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0858. Min Act: -0.0003

Data Index: 721230 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0777. Min Act: -0.0003

Data Index: 561172 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0760. Min Act: -0.0003

Data Index: 847738 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0754. Min Act: -0.0003

Data Index: 924513 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0754. Min Act: -0.0003

Data Index: 1017346 (C4 (Web Text))

Max Activating Token Index: 642

Text #5

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0725. Min Act: -0.0004

Data Index: 353990 (C4 (Web Text))

Max Activating Token Index: 780

Text #6

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0684. Min Act: -0.0003

Data Index: 47328 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0691. Min Act: -0.0003

Data Index: 822494 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0694. Min Act: -0.0003

Data Index: 1295188 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0671. Min Act: -0.0003

Data Index: 41828 (C4 (Web Text))

Max Activating Token Index: 825

Text #10

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0676. Min Act: -0.0004

Data Index: 336415 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0664. Min Act: -0.0003

Data Index: 259190 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0676. Min Act: -0.0003

Data Index: 690796 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0655. Min Act: -0.0003

Data Index: 1052522 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0669. Min Act: -0.0003

Data Index: 415531 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0654. Min Act: -0.0004

Data Index: 276539 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0649. Min Act: -0.0004

Data Index: 322980 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0633. Min Act: -0.0004

Data Index: 134959 (C4 (Web Text))

Max Activating Token Index: 685

Text #18

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0651. Min Act: -0.0003

Data Index: 502195 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 0.0858. Min Range: -0.0858

Max Act: 0.0634. Min Act: -0.0004

Data Index: 1317518 (C4 (Web Text))

Max Activating Token Index: 407