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

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

Neuron 4064 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2968. Min Act: -0.0000

Data Index: 514393 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2163. Min Act: -0.0000

Data Index: 1227713 (C4 (Web Text))

Max Activating Token Index: 721

Text #2

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1934. Min Act: -0.0000

Data Index: 292461 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.2027. Min Act: -0.0000

Data Index: 848050 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1874. Min Act: -0.0000

Data Index: 432934 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1723. Min Act: -0.0000

Data Index: 281887 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1601. Min Act: -0.0000

Data Index: 836069 (C4 (Web Text))

Max Activating Token Index: 723

Text #7

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1636. Min Act: -0.0000

Data Index: 28364 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1522198 (Python Code)

Max Activating Token Index: 293

Text #9

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1188888 (C4 (Web Text))

Max Activating Token Index: 807

Text #10

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1549. Min Act: -0.0000

Data Index: 503355 (C4 (Web Text))

Max Activating Token Index: 932

Text #11

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1768. Min Act: -0.0000

Data Index: 1295833 (C4 (Web Text))

Max Activating Token Index: 1006

Text #12

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1167415 (C4 (Web Text))

Max Activating Token Index: 612

Text #13

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1526. Min Act: -0.0000

Data Index: 300498 (C4 (Web Text))

Max Activating Token Index: 909

Text #14

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1604. Min Act: -0.0000

Data Index: 903908 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1509. Min Act: -0.0000

Data Index: 552720 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1294121 (C4 (Web Text))

Max Activating Token Index: 555

Text #17

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1497. Min Act: -0.0000

Data Index: 1278716 (C4 (Web Text))

Max Activating Token Index: 344

Text #18

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1488. Min Act: -0.0000

Data Index: 550913 (C4 (Web Text))

Max Activating Token Index: 263

Text #19

Max Range: 0.2968. Min Range: -0.2968

Max Act: 0.1527. Min Act: -0.0000

Data Index: 607193 (C4 (Web Text))

Max Activating Token Index: 541