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

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

Neuron 4139 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1818. Min Act: -0.0000

Data Index: 681242 (C4 (Web Text))

Max Activating Token Index: 380

Text #1

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1142308 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1430. Min Act: -0.0000

Data Index: 256042 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1433. Min Act: -0.0000

Data Index: 513808 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1530. Min Act: -0.0000

Data Index: 201521 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1442. Min Act: -0.0000

Data Index: 1082342 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1358. Min Act: -0.0000

Data Index: 293115 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1229. Min Act: -0.0000

Data Index: 993601 (C4 (Web Text))

Max Activating Token Index: 1022

Text #8

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1219. Min Act: -0.0000

Data Index: 1080775 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1133. Min Act: -0.0000

Data Index: 159333 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1065. Min Act: -0.0000

Data Index: 901838 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1130. Min Act: -0.0000

Data Index: 630530 (C4 (Web Text))

Max Activating Token Index: 100

Text #12

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1164660 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1111. Min Act: -0.0000

Data Index: 254721 (C4 (Web Text))

Max Activating Token Index: 407

Text #14

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0999. Min Act: -0.0000

Data Index: 1092961 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1067. Min Act: -0.0000

Data Index: 669481 (C4 (Web Text))

Max Activating Token Index: 473

Text #16

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1029. Min Act: -0.0000

Data Index: 207429 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1558504 (Python Code)

Max Activating Token Index: 1003

Text #18

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.0935. Min Act: -0.0000

Data Index: 542970 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.1818. Min Range: -0.1818

Max Act: 0.1034. Min Act: -0.0000

Data Index: 741652 (C4 (Web Text))

Max Activating Token Index: 572