Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1864 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.2058. Min Act: -0.0001

Data Index: 1019883 (C4 (Web Text))

Max Activating Token Index: 379

Text #1

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.2042. Min Act: -0.0001

Data Index: 762387 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1854. Min Act: -0.0001

Data Index: 547418 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1740. Min Act: -0.0001

Data Index: 162251 (C4 (Web Text))

Max Activating Token Index: 790

Text #4

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1353133 (C4 (Web Text))

Max Activating Token Index: 319

Text #5

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1844. Min Act: -0.0001

Data Index: 787107 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1070681 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1755. Min Act: -0.0001

Data Index: 145692 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1714. Min Act: -0.0001

Data Index: 815732 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1729. Min Act: -0.0001

Data Index: 618437 (C4 (Web Text))

Max Activating Token Index: 176

Text #10

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1662. Min Act: -0.0001

Data Index: 243581 (C4 (Web Text))

Max Activating Token Index: 21

Text #11

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1590. Min Act: -0.0001

Data Index: 962028 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1593. Min Act: -0.0001

Data Index: 151786 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1614. Min Act: -0.0001

Data Index: 617165 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1636. Min Act: -0.0001

Data Index: 785234 (C4 (Web Text))

Max Activating Token Index: 506

Text #15

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1476. Min Act: -0.0001

Data Index: 345866 (C4 (Web Text))

Max Activating Token Index: 123

Text #16

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1521. Min Act: -0.0001

Data Index: 145331 (C4 (Web Text))

Max Activating Token Index: 875

Text #17

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1456. Min Act: -0.0001

Data Index: 1123094 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1489. Min Act: -0.0001

Data Index: 459215 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 0.2058. Min Range: -0.2058

Max Act: 0.1527. Min Act: -0.0001

Data Index: 422006 (C4 (Web Text))

Max Activating Token Index: 525