Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1279 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0059. Min Act: -0.0005

Data Index: 1526882 (Python Code)

Max Activating Token Index: 514

Text #1

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1579747 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1634125 (Python Code)

Max Activating Token Index: 147

Text #3

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1524548 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1478541 (Python Code)

Max Activating Token Index: 413

Text #5

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1609217 (Python Code)

Max Activating Token Index: 316

Text #6

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0056. Min Act: -0.0005

Data Index: 1457946 (Python Code)

Max Activating Token Index: 636

Text #7

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1420208 (Python Code)

Max Activating Token Index: 633

Text #8

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1630718 (Python Code)

Max Activating Token Index: 630

Text #9

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1377516 (Python Code)

Max Activating Token Index: 511

Text #10

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1371922 (Python Code)

Max Activating Token Index: 564

Text #11

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1467102 (Python Code)

Max Activating Token Index: 374

Text #12

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1397516 (Python Code)

Max Activating Token Index: 608

Text #13

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0006

Data Index: 1575989 (Python Code)

Max Activating Token Index: 141

Text #14

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1585396 (Python Code)

Max Activating Token Index: 834

Text #15

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0005

Data Index: 534326 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0053. Min Act: -0.0005

Data Index: 1396904 (Python Code)

Max Activating Token Index: 211

Text #17

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0006

Data Index: 1573187 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1362300 (Python Code)

Max Activating Token Index: 266

Text #19

Max Range: 0.0059. Min Range: -0.0059

Max Act: 0.0052. Min Act: -0.0005

Data Index: 1410409 (Python Code)

Max Activating Token Index: 85