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

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

Neuron 369 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: 0.1714. Min Range: -0.1714

Max Act: 0.1714. Min Act: -0.0002

Data Index: 1509436 (Python Code)

Max Activating Token Index: 123

Text #1

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1528. Min Act: -0.0002

Data Index: 1649694 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1298. Min Act: -0.0002

Data Index: 1482350 (Python Code)

Max Activating Token Index: 168

Text #3

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1285. Min Act: -0.0002

Data Index: 1592454 (Python Code)

Max Activating Token Index: 279

Text #4

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1312. Min Act: -0.0002

Data Index: 1419222 (Python Code)

Max Activating Token Index: 531

Text #5

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1222. Min Act: -0.0002

Data Index: 1644844 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1202411 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1157. Min Act: -0.0002

Data Index: 1546920 (Python Code)

Max Activating Token Index: 72

Text #8

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1484798 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1197. Min Act: -0.0002

Data Index: 1625643 (Python Code)

Max Activating Token Index: 568

Text #10

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1165. Min Act: -0.0002

Data Index: 1532285 (Python Code)

Max Activating Token Index: 50

Text #11

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1625217 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1103. Min Act: -0.0002

Data Index: 1546320 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1104. Min Act: -0.0002

Data Index: 1656313 (Python Code)

Max Activating Token Index: 727

Text #14

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1644925 (Python Code)

Max Activating Token Index: 900

Text #15

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1090. Min Act: -0.0002

Data Index: 1488070 (Python Code)

Max Activating Token Index: 135

Text #16

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1083. Min Act: -0.0002

Data Index: 1482082 (Python Code)

Max Activating Token Index: 992

Text #17

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1099. Min Act: -0.0002

Data Index: 1559652 (Python Code)

Max Activating Token Index: 494

Text #18

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1643823 (Python Code)

Max Activating Token Index: 651

Text #19

Max Range: 0.1714. Min Range: -0.1714

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1558586 (Python Code)

Max Activating Token Index: 167