Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4209 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1088. Min Act: -0.0002

Data Index: 926650 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1012. Min Act: -0.0002

Data Index: 245851 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1018. Min Act: -0.0002

Data Index: 1000624 (C4 (Web Text))

Max Activating Token Index: 57

Text #3

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1320083 (C4 (Web Text))

Max Activating Token Index: 835

Text #4

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1105. Min Act: -0.0002

Data Index: 377598 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0957. Min Act: -0.0002

Data Index: 885786 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0998. Min Act: -0.0002

Data Index: 412025 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1012617 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1025136 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.1030. Min Act: -0.0002

Data Index: 1171598 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0921. Min Act: -0.0002

Data Index: 421902 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0999. Min Act: -0.0002

Data Index: 214518 (C4 (Web Text))

Max Activating Token Index: 475

Text #12

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0978. Min Act: -0.0002

Data Index: 474478 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0875. Min Act: -0.0002

Data Index: 29910 (C4 (Web Text))

Max Activating Token Index: 684

Text #14

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0970. Min Act: -0.0002

Data Index: 790461 (C4 (Web Text))

Max Activating Token Index: 676

Text #15

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0876. Min Act: -0.0002

Data Index: 330637 (C4 (Web Text))

Max Activating Token Index: 317

Text #16

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0842. Min Act: -0.0002

Data Index: 278974 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0896. Min Act: -0.0002

Data Index: 325357 (C4 (Web Text))

Max Activating Token Index: 483

Text #18

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0816. Min Act: -0.0002

Data Index: 508354 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 0.1105. Min Range: -0.1105

Max Act: 0.0835. Min Act: -0.0002

Data Index: 494835 (C4 (Web Text))

Max Activating Token Index: 987