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

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

Neuron 1075 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.5067. Min Act: -0.0000

Data Index: 623571 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4815. Min Act: -0.0000

Data Index: 75629 (C4 (Web Text))

Max Activating Token Index: 780

Text #2

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4125. Min Act: -0.0000

Data Index: 961090 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4101. Min Act: -0.0000

Data Index: 1636968 (Python Code)

Max Activating Token Index: 770

Text #4

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.4058. Min Act: -0.0000

Data Index: 998525 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2971. Min Act: -0.0000

Data Index: 178109 (C4 (Web Text))

Max Activating Token Index: 833

Text #6

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3847. Min Act: -0.0000

Data Index: 1168167 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3388. Min Act: 0.0000

Data Index: 247045 (C4 (Web Text))

Max Activating Token Index: 145

Text #8

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3633. Min Act: -0.0000

Data Index: 1629387 (Python Code)

Max Activating Token Index: 621

Text #9

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1530320 (Python Code)

Max Activating Token Index: 912

Text #10

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3290. Min Act: -0.0000

Data Index: 972434 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3619. Min Act: -0.0000

Data Index: 435823 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.2943. Min Act: -0.0000

Data Index: 528916 (C4 (Web Text))

Max Activating Token Index: 873

Text #13

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3352. Min Act: -0.0000

Data Index: 952760 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1386041 (Python Code)

Max Activating Token Index: 683

Text #15

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3357. Min Act: -0.0000

Data Index: 1570354 (Python Code)

Max Activating Token Index: 858

Text #16

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3174. Min Act: -0.0000

Data Index: 1404488 (Python Code)

Max Activating Token Index: 981

Text #17

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3122. Min Act: -0.0000

Data Index: 67029 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3032. Min Act: -0.0000

Data Index: 1216537 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 0.5067. Min Range: -0.5067

Max Act: 0.3381. Min Act: -0.0000

Data Index: 312191 (C4 (Web Text))

Max Activating Token Index: 537