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

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

Neuron 2018 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: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0005

Data Index: 910070 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0005

Data Index: 552350 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0005

Data Index: 138680 (C4 (Web Text))

Max Activating Token Index: 635

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0006

Data Index: 1337278 (C4 (Web Text))

Max Activating Token Index: 725

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0077. Min Act: -0.0005

Data Index: 901078 (C4 (Web Text))

Max Activating Token Index: 97

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0005

Data Index: 1143895 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0075. Min Act: -0.0006

Data Index: 989156 (C4 (Web Text))

Max Activating Token Index: 440

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1352905 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1248922 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0074. Min Act: -0.0005

Data Index: 1042143 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0005

Data Index: 617621 (C4 (Web Text))

Max Activating Token Index: 641

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0005

Data Index: 1017997 (C4 (Web Text))

Max Activating Token Index: 921

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0005

Data Index: 440306 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0072. Min Act: -0.0005

Data Index: 908506 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1406185 (Python Code)

Max Activating Token Index: 630

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0006

Data Index: 1337380 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0005

Data Index: 486628 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0071. Min Act: -0.0005

Data Index: 1005877 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1275584 (C4 (Web Text))

Max Activating Token Index: 161

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0070. Min Act: -0.0005

Data Index: 126106 (C4 (Web Text))

Max Activating Token Index: 289