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

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

Neuron 2444 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1006836 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0121. Min Act: -0.0000

Data Index: 185682 (C4 (Web Text))

Max Activating Token Index: 54

Text #2

Max Range: 1.1902. Min Range: -1.1902

Max Act: 1.0093. Min Act: -0.0000

Data Index: 915068 (C4 (Web Text))

Max Activating Token Index: 770

Text #3

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9280. Min Act: -0.0000

Data Index: 975494 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8823. Min Act: -0.0000

Data Index: 651969 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9628. Min Act: -0.0000

Data Index: 1006516 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1358040 (C4 (Web Text))

Max Activating Token Index: 110

Text #7

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9450. Min Act: -0.0000

Data Index: 16866 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9367. Min Act: -0.0000

Data Index: 1075490 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.9019. Min Act: -0.0000

Data Index: 993198 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8594. Min Act: -0.0000

Data Index: 254355 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8188. Min Act: -0.0000

Data Index: 269826 (C4 (Web Text))

Max Activating Token Index: 201

Text #12

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8768. Min Act: -0.0000

Data Index: 912866 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8473. Min Act: -0.0000

Data Index: 1069512 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1100598 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8712. Min Act: -0.0000

Data Index: 740077 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7795. Min Act: -0.0000

Data Index: 203032 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8065. Min Act: -0.0000

Data Index: 1314574 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.7599. Min Act: -0.0000

Data Index: 1175841 (C4 (Web Text))

Max Activating Token Index: 967

Text #19

Max Range: 1.1902. Min Range: -1.1902

Max Act: 0.8246. Min Act: -0.0000

Data Index: 1289602 (C4 (Web Text))

Max Activating Token Index: 781