Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3477 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.3424. Min Act: -0.0000

Data Index: 355439 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1913. Min Act: -0.0000

Data Index: 965256 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.2056. Min Act: -0.0000

Data Index: 905731 (C4 (Web Text))

Max Activating Token Index: 466

Text #3

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1936. Min Act: -0.0000

Data Index: 123127 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1946. Min Act: -0.0000

Data Index: 43853 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1974. Min Act: -0.0000

Data Index: 787944 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1874. Min Act: -0.0000

Data Index: 895837 (C4 (Web Text))

Max Activating Token Index: 347

Text #7

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1153686 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1179983 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1792. Min Act: -0.0000

Data Index: 172035 (C4 (Web Text))

Max Activating Token Index: 32

Text #10

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1850. Min Act: -0.0000

Data Index: 381343 (C4 (Web Text))

Max Activating Token Index: 736

Text #11

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1734. Min Act: -0.0000

Data Index: 349043 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1757. Min Act: -0.0000

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 648

Text #13

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1648. Min Act: -0.0000

Data Index: 434257 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1536. Min Act: -0.0000

Data Index: 382200 (C4 (Web Text))

Max Activating Token Index: 862

Text #15

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1326500 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1526. Min Act: -0.0000

Data Index: 445881 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1505. Min Act: -0.0000

Data Index: 1403647 (Python Code)

Max Activating Token Index: 304

Text #18

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1000222 (C4 (Web Text))

Max Activating Token Index: 415

Text #19

Max Range: 0.3424. Min Range: -0.3424

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1053775 (C4 (Web Text))

Max Activating Token Index: 689