Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1879 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0001

Data Index: 1409188 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0001

Data Index: 1502862 (Python Code)

Max Activating Token Index: 955

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0001

Data Index: 1586578 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0001

Data Index: 1388994 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0001

Data Index: 1434388 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0001

Data Index: 1575520 (Python Code)

Max Activating Token Index: 969

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1576180 (Python Code)

Max Activating Token Index: 713

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1408391 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1597151 (Python Code)

Max Activating Token Index: 221

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1617034 (Python Code)

Max Activating Token Index: 981

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0001

Data Index: 1655813 (Python Code)

Max Activating Token Index: 989

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1635446 (Python Code)

Max Activating Token Index: 1002

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0001

Data Index: 1430811 (Python Code)

Max Activating Token Index: 582

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0001

Data Index: 1539832 (Python Code)

Max Activating Token Index: 999

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1488555 (Python Code)

Max Activating Token Index: 511

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0001

Data Index: 1622930 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0001

Data Index: 1461410 (Python Code)

Max Activating Token Index: 974

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0001

Data Index: 1639105 (Python Code)

Max Activating Token Index: 896

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0001

Data Index: 1376637 (Python Code)

Max Activating Token Index: 950

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0060. Min Act: -0.0001

Data Index: 1631019 (Python Code)

Max Activating Token Index: 919