Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 568 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0103. Min Act: -0.0003

Data Index: 944785 (C4 (Web Text))

Max Activating Token Index: 935

Text #1

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0079. Min Act: -0.0003

Data Index: 316559 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0075. Min Act: -0.0003

Data Index: 1084306 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0080. Min Act: -0.0003

Data Index: 568501 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0074. Min Act: -0.0003

Data Index: 733701 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0073. Min Act: -0.0003

Data Index: 835469 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0074. Min Act: -0.0004

Data Index: 83784 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0070. Min Act: -0.0003

Data Index: 1088444 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0071. Min Act: -0.0003

Data Index: 1353208 (C4 (Web Text))

Max Activating Token Index: 875

Text #9

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0068. Min Act: -0.0003

Data Index: 651734 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0075. Min Act: -0.0003

Data Index: 803311 (C4 (Web Text))

Max Activating Token Index: 842

Text #11

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0074. Min Act: -0.0003

Data Index: 641663 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0070. Min Act: -0.0004

Data Index: 543610 (C4 (Web Text))

Max Activating Token Index: 736

Text #13

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0068. Min Act: -0.0003

Data Index: 1407125 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0068. Min Act: -0.0003

Data Index: 130985 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0069. Min Act: -0.0003

Data Index: 1594078 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0070. Min Act: -0.0004

Data Index: 1358710 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0070. Min Act: -0.0004

Data Index: 429521 (C4 (Web Text))

Max Activating Token Index: 654

Text #18

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1567326 (Python Code)

Max Activating Token Index: 521

Text #19

Max Range: 0.0103. Min Range: -0.0103

Max Act: 0.0062. Min Act: -0.0003

Data Index: 1182333 (C4 (Web Text))

Max Activating Token Index: 531