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

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

Neuron 557 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2346. Min Act: -0.0005

Data Index: 969861 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2087. Min Act: -0.0005

Data Index: 444250 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2195. Min Act: -0.0005

Data Index: 455738 (C4 (Web Text))

Max Activating Token Index: 510

Text #3

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2058. Min Act: -0.0005

Data Index: 376069 (C4 (Web Text))

Max Activating Token Index: 782

Text #4

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2026. Min Act: -0.0005

Data Index: 1053395 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2077. Min Act: -0.0005

Data Index: 376920 (C4 (Web Text))

Max Activating Token Index: 698

Text #6

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.2065. Min Act: -0.0005

Data Index: 556896 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1969. Min Act: -0.0005

Data Index: 247389 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1993. Min Act: -0.0005

Data Index: 1245621 (C4 (Web Text))

Max Activating Token Index: 489

Text #9

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1951. Min Act: -0.0005

Data Index: 138787 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1892. Min Act: -0.0005

Data Index: 909594 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1917. Min Act: -0.0005

Data Index: 498435 (C4 (Web Text))

Max Activating Token Index: 970

Text #12

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1957. Min Act: -0.0005

Data Index: 209579 (C4 (Web Text))

Max Activating Token Index: 724

Text #13

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1866. Min Act: -0.0005

Data Index: 1287235 (C4 (Web Text))

Max Activating Token Index: 395

Text #14

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1776. Min Act: -0.0005

Data Index: 1149078 (C4 (Web Text))

Max Activating Token Index: 455

Text #15

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1861. Min Act: -0.0005

Data Index: 293353 (C4 (Web Text))

Max Activating Token Index: 19

Text #16

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1809. Min Act: -0.0005

Data Index: 953425 (C4 (Web Text))

Max Activating Token Index: 873

Text #17

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1904. Min Act: -0.0005

Data Index: 1244408 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1863. Min Act: -0.0005

Data Index: 1007406 (C4 (Web Text))

Max Activating Token Index: 454

Text #19

Max Range: 0.2346. Min Range: -0.2346

Max Act: 0.1726. Min Act: -0.0005

Data Index: 1209839 (C4 (Web Text))

Max Activating Token Index: 727