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

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

Neuron 2025 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0104. Min Act: -0.0005

Data Index: 1568980 (Python Code)

Max Activating Token Index: 120

Text #1

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1607545 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1594568 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1545446 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1526811 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0094. Min Act: -0.0005

Data Index: 1653069 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1440805 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0092. Min Act: -0.0005

Data Index: 1466954 (Python Code)

Max Activating Token Index: 48

Text #8

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0089. Min Act: -0.0005

Data Index: 760548 (C4 (Web Text))

Max Activating Token Index: 931

Text #9

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0089. Min Act: -0.0005

Data Index: 1591678 (Python Code)

Max Activating Token Index: 87

Text #10

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0087. Min Act: -0.0005

Data Index: 1450921 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1576659 (Python Code)

Max Activating Token Index: 484

Text #12

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0085. Min Act: -0.0005

Data Index: 1477259 (Python Code)

Max Activating Token Index: 915

Text #13

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0084. Min Act: -0.0005

Data Index: 1384787 (Python Code)

Max Activating Token Index: 345

Text #14

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1375926 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1474735 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1374440 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1505032 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1364690 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.0104. Min Range: -0.0104

Max Act: 0.0083. Min Act: -0.0005

Data Index: 1487812 (Python Code)

Max Activating Token Index: 1