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

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

Neuron 3340 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.9312. Min Act: -0.0001

Data Index: 587220 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8599. Min Act: -0.0001

Data Index: 668658 (C4 (Web Text))

Max Activating Token Index: 723

Text #2

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8790. Min Act: -0.0001

Data Index: 358970 (C4 (Web Text))

Max Activating Token Index: 206

Text #3

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8987. Min Act: -0.0001

Data Index: 246459 (C4 (Web Text))

Max Activating Token Index: 98

Text #4

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8636. Min Act: -0.0001

Data Index: 703263 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7926. Min Act: -0.0001

Data Index: 879778 (C4 (Web Text))

Max Activating Token Index: 139

Text #6

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7808. Min Act: -0.0001

Data Index: 1330314 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.8108. Min Act: -0.0001

Data Index: 1076994 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7162. Min Act: -0.0001

Data Index: 121334 (C4 (Web Text))

Max Activating Token Index: 642

Text #9

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7601. Min Act: -0.0001

Data Index: 966689 (C4 (Web Text))

Max Activating Token Index: 46

Text #10

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7892. Min Act: -0.0001

Data Index: 295298 (C4 (Web Text))

Max Activating Token Index: 166

Text #11

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7447. Min Act: -0.0001

Data Index: 48007 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7478. Min Act: -0.0001

Data Index: 306194 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6935. Min Act: -0.0001

Data Index: 340284 (C4 (Web Text))

Max Activating Token Index: 405

Text #14

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1278349 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7052. Min Act: -0.0001

Data Index: 690911 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6816. Min Act: -0.0001

Data Index: 1162916 (C4 (Web Text))

Max Activating Token Index: 808

Text #17

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.7226. Min Act: -0.0001

Data Index: 1182012 (C4 (Web Text))

Max Activating Token Index: 676

Text #18

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6506. Min Act: -0.0001

Data Index: 276440 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.9312. Min Range: -0.9312

Max Act: 0.6217. Min Act: -0.0001

Data Index: 59791 (C4 (Web Text))

Max Activating Token Index: 848