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

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

Neuron 1805 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: 0.0622. Min Range: -0.0622

Max Act: 0.0622. Min Act: -0.0003

Data Index: 824567 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0618. Min Act: -0.0004

Data Index: 986710 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0616. Min Act: -0.0003

Data Index: 794444 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0607. Min Act: -0.0003

Data Index: 476124 (C4 (Web Text))

Max Activating Token Index: 953

Text #4

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0601. Min Act: -0.0002

Data Index: 691817 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0601. Min Act: -0.0003

Data Index: 994371 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0584. Min Act: -0.0003

Data Index: 662115 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0583. Min Act: -0.0003

Data Index: 185136 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0595. Min Act: -0.0003

Data Index: 1153304 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0565. Min Act: -0.0003

Data Index: 1188408 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0562. Min Act: -0.0003

Data Index: 723078 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0579. Min Act: -0.0002

Data Index: 541899 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0561. Min Act: -0.0003

Data Index: 974937 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0560. Min Act: -0.0003

Data Index: 1057130 (C4 (Web Text))

Max Activating Token Index: 253

Text #14

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0557. Min Act: -0.0002

Data Index: 222752 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0559. Min Act: -0.0002

Data Index: 721112 (C4 (Web Text))

Max Activating Token Index: 1015

Text #16

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0548. Min Act: -0.0003

Data Index: 462376 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0547. Min Act: -0.0003

Data Index: 543321 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0545. Min Act: -0.0003

Data Index: 558990 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0545. Min Act: -0.0003

Data Index: 888525 (C4 (Web Text))

Max Activating Token Index: 542