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

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

Neuron 1479 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: 0.0086. Min Range: -0.0086

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1403383 (Python Code)

Max Activating Token Index: 596

Text #1

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0084. Min Act: -0.0006

Data Index: 767546 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0084. Min Act: -0.0006

Data Index: 567534 (C4 (Web Text))

Max Activating Token Index: 150

Text #3

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0081. Min Act: -0.0006

Data Index: 147788 (C4 (Web Text))

Max Activating Token Index: 602

Text #4

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0080. Min Act: -0.0006

Data Index: 887128 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1487558 (Python Code)

Max Activating Token Index: 693

Text #6

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0076. Min Act: -0.0006

Data Index: 893905 (C4 (Web Text))

Max Activating Token Index: 909

Text #7

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0006

Data Index: 247600 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1567609 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1458131 (Python Code)

Max Activating Token Index: 628

Text #10

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0072. Min Act: -0.0006

Data Index: 1127628 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0006

Data Index: 226588 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1489480 (Python Code)

Max Activating Token Index: 845

Text #13

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1545499 (Python Code)

Max Activating Token Index: 278

Text #14

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0005

Data Index: 117183 (C4 (Web Text))

Max Activating Token Index: 221

Text #15

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0005

Data Index: 109511 (C4 (Web Text))

Max Activating Token Index: 764

Text #16

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0005

Data Index: 158062 (C4 (Web Text))

Max Activating Token Index: 703

Text #17

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0068. Min Act: -0.0005

Data Index: 1558626 (Python Code)

Max Activating Token Index: 745

Text #18

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0071. Min Act: -0.0005

Data Index: 118856 (C4 (Web Text))

Max Activating Token Index: 391

Text #19

Max Range: 0.0086. Min Range: -0.0086

Max Act: 0.0070. Min Act: -0.0005

Data Index: 1528605 (Python Code)

Max Activating Token Index: 834