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

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

Neuron 1905 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1119. Min Act: -0.0006

Data Index: 1526728 (Python Code)

Max Activating Token Index: 507

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0006

Data Index: 1530046 (Python Code)

Max Activating Token Index: 123

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1116. Min Act: -0.0006

Data Index: 1628559 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1105. Min Act: -0.0006

Data Index: 1413540 (Python Code)

Max Activating Token Index: 313

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1066. Min Act: -0.0006

Data Index: 1422899 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1131. Min Act: -0.0006

Data Index: 1645491 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1020. Min Act: -0.0006

Data Index: 1502177 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1101. Min Act: -0.0006

Data Index: 1392385 (Python Code)

Max Activating Token Index: 649

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1005. Min Act: -0.0006

Data Index: 1413053 (Python Code)

Max Activating Token Index: 261

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0960. Min Act: -0.0006

Data Index: 1613779 (Python Code)

Max Activating Token Index: 463

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1006. Min Act: -0.0006

Data Index: 1584978 (Python Code)

Max Activating Token Index: 44

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1090. Min Act: -0.0006

Data Index: 1605585 (Python Code)

Max Activating Token Index: 98

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1020. Min Act: -0.0006

Data Index: 1533439 (Python Code)

Max Activating Token Index: 101

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1016. Min Act: -0.0006

Data Index: 1587771 (Python Code)

Max Activating Token Index: 94

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0993. Min Act: -0.0006

Data Index: 1431477 (Python Code)

Max Activating Token Index: 422

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1030. Min Act: -0.0006

Data Index: 1519052 (Python Code)

Max Activating Token Index: 216

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0982. Min Act: -0.0006

Data Index: 1586308 (Python Code)

Max Activating Token Index: 251

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1006. Min Act: -0.0006

Data Index: 1547288 (Python Code)

Max Activating Token Index: 626

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0941. Min Act: -0.0006

Data Index: 1614851 (Python Code)

Max Activating Token Index: 633

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1006. Min Act: -0.0006

Data Index: 1512600 (Python Code)

Max Activating Token Index: 143