Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 514 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.6622. Min Act: -0.0000

Data Index: 418773 (C4 (Web Text))

Max Activating Token Index: 964

Text #1

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5809. Min Act: -0.0000

Data Index: 748231 (C4 (Web Text))

Max Activating Token Index: 265

Text #2

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1152591 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.6618. Min Act: -0.0000

Data Index: 1116426 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5779. Min Act: -0.0000

Data Index: 125943 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5590. Min Act: -0.0000

Data Index: 946242 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5635. Min Act: -0.0000

Data Index: 1457899 (Python Code)

Max Activating Token Index: 887

Text #7

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5238. Min Act: -0.0000

Data Index: 638211 (C4 (Web Text))

Max Activating Token Index: 985

Text #8

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5460. Min Act: -0.0000

Data Index: 935460 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1329888 (C4 (Web Text))

Max Activating Token Index: 963

Text #10

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5211. Min Act: -0.0000

Data Index: 872271 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5094. Min Act: -0.0000

Data Index: 111062 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5245. Min Act: -0.0000

Data Index: 411740 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5201. Min Act: -0.0000

Data Index: 44767 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5028. Min Act: -0.0000

Data Index: 867760 (C4 (Web Text))

Max Activating Token Index: 687

Text #15

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1198664 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4830. Min Act: -0.0000

Data Index: 169344 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4743. Min Act: -0.0000

Data Index: 264570 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4889. Min Act: -0.0000

Data Index: 747717 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.6622. Min Range: -0.6622

Max Act: 0.4890. Min Act: 0.0000

Data Index: 542534 (C4 (Web Text))

Max Activating Token Index: 962