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

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

Neuron 573 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0836. Min Act: -0.0001

Data Index: 252374 (C4 (Web Text))

Max Activating Token Index: 763

Text #1

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0745. Min Act: -0.0001

Data Index: 624278 (C4 (Web Text))

Max Activating Token Index: 521

Text #2

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0713. Min Act: -0.0001

Data Index: 1106649 (C4 (Web Text))

Max Activating Token Index: 990

Text #3

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0707. Min Act: -0.0002

Data Index: 416284 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0683. Min Act: -0.0001

Data Index: 556739 (C4 (Web Text))

Max Activating Token Index: 871

Text #5

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0740. Min Act: -0.0002

Data Index: 110577 (C4 (Web Text))

Max Activating Token Index: 799

Text #6

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0705. Min Act: -0.0002

Data Index: 1017563 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0710. Min Act: -0.0001

Data Index: 895560 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0703. Min Act: -0.0002

Data Index: 200474 (C4 (Web Text))

Max Activating Token Index: 657

Text #9

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0672. Min Act: -0.0002

Data Index: 933272 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0679. Min Act: -0.0002

Data Index: 318113 (C4 (Web Text))

Max Activating Token Index: 142

Text #11

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0651. Min Act: -0.0001

Data Index: 1239231 (C4 (Web Text))

Max Activating Token Index: 873

Text #12

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0657. Min Act: -0.0002

Data Index: 537198 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1152781 (C4 (Web Text))

Max Activating Token Index: 305

Text #14

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0652. Min Act: -0.0002

Data Index: 223128 (C4 (Web Text))

Max Activating Token Index: 601

Text #15

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1166893 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1356452 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1278724 (C4 (Web Text))

Max Activating Token Index: 183

Text #18

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0658. Min Act: -0.0001

Data Index: 1223887 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.0836. Min Range: -0.0836

Max Act: 0.0646. Min Act: -0.0001

Data Index: 429245 (C4 (Web Text))

Max Activating Token Index: 850