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

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

Neuron 2169 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.5672. Min Act: -0.0001

Data Index: 401915 (C4 (Web Text))

Max Activating Token Index: 744

Text #1

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4007. Min Act: -0.0001

Data Index: 1282029 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3613. Min Act: -0.0001

Data Index: 196662 (C4 (Web Text))

Max Activating Token Index: 208

Text #3

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3230. Min Act: -0.0001

Data Index: 1441801 (Python Code)

Max Activating Token Index: 854

Text #4

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1019614 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.3719. Min Act: -0.0001

Data Index: 1608959 (Python Code)

Max Activating Token Index: 934

Text #6

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.2724. Min Act: -0.0001

Data Index: 896764 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.2503. Min Act: -0.0001

Data Index: 740369 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.4041. Min Act: -0.0001

Data Index: 569002 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.2338. Min Act: -0.0001

Data Index: 329382 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1940. Min Act: -0.0001

Data Index: 258661 (C4 (Web Text))

Max Activating Token Index: 558

Text #11

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.2094. Min Act: -0.0001

Data Index: 601563 (C4 (Web Text))

Max Activating Token Index: 223

Text #12

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1913. Min Act: -0.0001

Data Index: 235805 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.2132. Min Act: -0.0001

Data Index: 1088115 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1371. Min Act: -0.0001

Data Index: 136371 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1936. Min Act: -0.0001

Data Index: 290142 (C4 (Web Text))

Max Activating Token Index: 583

Text #16

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1765. Min Act: -0.0001

Data Index: 369202 (C4 (Web Text))

Max Activating Token Index: 639

Text #17

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1682. Min Act: -0.0001

Data Index: 1643729 (Python Code)

Max Activating Token Index: 314

Text #18

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1988. Min Act: -0.0001

Data Index: 500698 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 0.5672. Min Range: -0.5672

Max Act: 0.1758. Min Act: -0.0001

Data Index: 752725 (C4 (Web Text))

Max Activating Token Index: 229