Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1102 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0058. Min Act: -0.0002

Data Index: 1539936 (Python Code)

Max Activating Token Index: 128

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0002

Data Index: 919224 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1440283 (Python Code)

Max Activating Token Index: 928

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0002

Data Index: 1581485 (Python Code)

Max Activating Token Index: 752

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0001

Data Index: 709011 (C4 (Web Text))

Max Activating Token Index: 887

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0001

Data Index: 1421410 (Python Code)

Max Activating Token Index: 800

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0001

Data Index: 1457812 (Python Code)

Max Activating Token Index: 573

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1377847 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0000

Data Index: 1476045 (Python Code)

Max Activating Token Index: 231

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0055. Min Act: -0.0002

Data Index: 1598460 (Python Code)

Max Activating Token Index: 899

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0001

Data Index: 1603900 (Python Code)

Max Activating Token Index: 954

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1489240 (Python Code)

Max Activating Token Index: 253

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0002

Data Index: 1408601 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0002

Data Index: 82729 (C4 (Web Text))

Max Activating Token Index: 311

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1449698 (Python Code)

Max Activating Token Index: 940

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1470882 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0001

Data Index: 1368266 (Python Code)

Max Activating Token Index: 196

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0002

Data Index: 1459651 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0002

Data Index: 1414351 (Python Code)

Max Activating Token Index: 281

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0051. Min Act: -0.0001

Data Index: 1443603 (Python Code)

Max Activating Token Index: 790