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

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

Neuron 2909 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.5798. Min Act: -0.0000

Data Index: 664304 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.4534. Min Act: -0.0000

Data Index: 1078172 (C4 (Web Text))

Max Activating Token Index: 1014

Text #2

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.4315. Min Act: -0.0000

Data Index: 1147410 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2836. Min Act: -0.0000

Data Index: 450404 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2505. Min Act: -0.0000

Data Index: 137134 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1030. Min Act: -0.0000

Data Index: 678608 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1739. Min Act: -0.0000

Data Index: 697600 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0375. Min Act: -0.0000

Data Index: 1066794 (C4 (Web Text))

Max Activating Token Index: 299

Text #8

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0709. Min Act: -0.0000

Data Index: 1139966 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.2886. Min Act: -0.0000

Data Index: 155110 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0208. Min Act: -0.0000

Data Index: 847683 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0866. Min Act: -0.0000

Data Index: 958907 (C4 (Web Text))

Max Activating Token Index: 847

Text #12

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1099. Min Act: -0.0000

Data Index: 1276074 (C4 (Web Text))

Max Activating Token Index: 549

Text #13

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0932. Min Act: -0.0000

Data Index: 220502 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.1930. Min Act: -0.0000

Data Index: 1060292 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0561. Min Act: -0.0000

Data Index: 992517 (C4 (Web Text))

Max Activating Token Index: 30

Text #16

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0834. Min Act: -0.0000

Data Index: 473257 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 2.5798. Min Range: -2.5798

Max Act: 1.9373. Min Act: -0.0000

Data Index: 1223732 (C4 (Web Text))

Max Activating Token Index: 278

Text #18

Max Range: 2.5798. Min Range: -2.5798

Max Act: 1.9669. Min Act: -0.0000

Data Index: 625298 (C4 (Web Text))

Max Activating Token Index: 845

Text #19

Max Range: 2.5798. Min Range: -2.5798

Max Act: 2.0844. Min Act: -0.0000

Data Index: 630668 (C4 (Web Text))

Max Activating Token Index: 31