Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1789 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2760. Min Act: -0.0002

Data Index: 1252766 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2497. Min Act: -0.0002

Data Index: 136353 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2355. Min Act: -0.0002

Data Index: 560074 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2478. Min Act: -0.0002

Data Index: 118609 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2245. Min Act: -0.0002

Data Index: 642738 (C4 (Web Text))

Max Activating Token Index: 282

Text #5

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2294. Min Act: -0.0002

Data Index: 654578 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2354. Min Act: -0.0002

Data Index: 511564 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2086. Min Act: -0.0002

Data Index: 1348599 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2093. Min Act: -0.0002

Data Index: 929168 (C4 (Web Text))

Max Activating Token Index: 479

Text #9

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2168. Min Act: -0.0002

Data Index: 1145157 (C4 (Web Text))

Max Activating Token Index: 786

Text #10

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2119. Min Act: -0.0002

Data Index: 17848 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2010. Min Act: -0.0002

Data Index: 1325387 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2118. Min Act: -0.0002

Data Index: 278649 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2047. Min Act: -0.0002

Data Index: 1049617 (C4 (Web Text))

Max Activating Token Index: 399

Text #14

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2041. Min Act: -0.0002

Data Index: 903799 (C4 (Web Text))

Max Activating Token Index: 154

Text #15

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2110. Min Act: -0.0002

Data Index: 1312951 (C4 (Web Text))

Max Activating Token Index: 207

Text #16

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2042. Min Act: -0.0002

Data Index: 300396 (C4 (Web Text))

Max Activating Token Index: 845

Text #17

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2159. Min Act: -0.0002

Data Index: 1333885 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2086. Min Act: -0.0002

Data Index: 1325449 (C4 (Web Text))

Max Activating Token Index: 383

Text #19

Max Range: 0.2760. Min Range: -0.2760

Max Act: 0.2056. Min Act: -0.0002

Data Index: 38360 (C4 (Web Text))

Max Activating Token Index: 1013