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

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

Neuron 1207 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: 0.0076. Min Range: -0.0076

Max Act: 0.0076. Min Act: -0.0006

Data Index: 1066152 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0076. Min Act: -0.0005

Data Index: 392825 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0068. Min Act: -0.0006

Data Index: 184030 (C4 (Web Text))

Max Activating Token Index: 381

Text #3

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0060. Min Act: -0.0005

Data Index: 451521 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0058. Min Act: -0.0005

Data Index: 1168981 (C4 (Web Text))

Max Activating Token Index: 493

Text #5

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1566495 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0056. Min Act: -0.0005

Data Index: 418387 (C4 (Web Text))

Max Activating Token Index: 60

Text #7

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0055. Min Act: -0.0005

Data Index: 1172388 (C4 (Web Text))

Max Activating Token Index: 508

Text #8

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0057. Min Act: -0.0005

Data Index: 1221394 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0056. Min Act: -0.0006

Data Index: 555057 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0054. Min Act: -0.0005

Data Index: 1567581 (Python Code)

Max Activating Token Index: 6

Text #11

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0054. Min Act: -0.0005

Data Index: 34084 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0051. Min Act: -0.0006

Data Index: 1134671 (C4 (Web Text))

Max Activating Token Index: 311

Text #13

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0051. Min Act: -0.0005

Data Index: 104321 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1479178 (Python Code)

Max Activating Token Index: 5

Text #15

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0051. Min Act: -0.0005

Data Index: 551892 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0051. Min Act: -0.0005

Data Index: 1505341 (Python Code)

Max Activating Token Index: 2

Text #17

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0050. Min Act: -0.0005

Data Index: 1525144 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0050. Min Act: -0.0005

Data Index: 1569863 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.0076. Min Range: -0.0076

Max Act: 0.0050. Min Act: -0.0005

Data Index: 1469245 (Python Code)

Max Activating Token Index: 3