Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 323 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0051. Min Act: -0.0001

Data Index: 536147 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0049. Min Act: -0.0001

Data Index: 1597818 (Python Code)

Max Activating Token Index: 954

Text #2

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0048. Min Act: -0.0001

Data Index: 1460942 (Python Code)

Max Activating Token Index: 995

Text #3

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0043. Min Act: -0.0000

Data Index: 1613426 (Python Code)

Max Activating Token Index: 995

Text #4

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0042. Min Act: -0.0000

Data Index: 1628778 (Python Code)

Max Activating Token Index: 1021

Text #5

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0043. Min Act: -0.0000

Data Index: 1643249 (Python Code)

Max Activating Token Index: 950

Text #6

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0044. Min Act: -0.0000

Data Index: 1396559 (Python Code)

Max Activating Token Index: 830

Text #7

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0044. Min Act: -0.0000

Data Index: 1499952 (Python Code)

Max Activating Token Index: 902

Text #8

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0040. Min Act: -0.0000

Data Index: 1460070 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0037. Min Act: -0.0001

Data Index: 812026 (C4 (Web Text))

Max Activating Token Index: 986

Text #10

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0040. Min Act: -0.0001

Data Index: 884094 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0036. Min Act: -0.0001

Data Index: 1644731 (Python Code)

Max Activating Token Index: 944

Text #12

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0039. Min Act: -0.0001

Data Index: 1413439 (Python Code)

Max Activating Token Index: 854

Text #13

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0038. Min Act: -0.0001

Data Index: 1534150 (Python Code)

Max Activating Token Index: 968

Text #14

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0038. Min Act: -0.0000

Data Index: 1516135 (Python Code)

Max Activating Token Index: 162

Text #15

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0037. Min Act: -0.0001

Data Index: 1509343 (Python Code)

Max Activating Token Index: 258

Text #16

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0041. Min Act: -0.0001

Data Index: 1424886 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0042. Min Act: -0.0000

Data Index: 1367624 (Python Code)

Max Activating Token Index: 859

Text #18

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0039. Min Act: -0.0001

Data Index: 1492718 (Python Code)

Max Activating Token Index: 250

Text #19

Max Range: 0.0051. Min Range: -0.0051

Max Act: 0.0040. Min Act: -0.0001

Data Index: 1448044 (Python Code)

Max Activating Token Index: 880