Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2305 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2283. Min Act: -0.0000

Data Index: 46796 (C4 (Web Text))

Max Activating Token Index: 201

Text #1

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2440. Min Act: -0.0000

Data Index: 17367 (C4 (Web Text))

Max Activating Token Index: 970

Text #2

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2032. Min Act: -0.0000

Data Index: 199035 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2789. Min Act: -0.0000

Data Index: 522103 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.2161. Min Act: -0.0000

Data Index: 412308 (C4 (Web Text))

Max Activating Token Index: 613

Text #5

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1949. Min Act: -0.0000

Data Index: 367227 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1204. Min Act: -0.0000

Data Index: 1315287 (C4 (Web Text))

Max Activating Token Index: 219

Text #7

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1596. Min Act: -0.0000

Data Index: 612300 (C4 (Web Text))

Max Activating Token Index: 699

Text #8

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1556. Min Act: -0.0000

Data Index: 948095 (C4 (Web Text))

Max Activating Token Index: 674

Text #9

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0374. Min Act: -0.0000

Data Index: 21717 (C4 (Web Text))

Max Activating Token Index: 286

Text #10

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1036. Min Act: -0.0000

Data Index: 124392 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.1133. Min Act: -0.0000

Data Index: 744548 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0841. Min Act: -0.0000

Data Index: 344287 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0645. Min Act: -0.0000

Data Index: 1302835 (C4 (Web Text))

Max Activating Token Index: 480

Text #14

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9869. Min Act: -0.0000

Data Index: 470254 (C4 (Web Text))

Max Activating Token Index: 763

Text #15

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0679. Min Act: -0.0000

Data Index: 728574 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0908. Min Act: -0.0000

Data Index: 1038309 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0113. Min Act: -0.0000

Data Index: 869199 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 1.2789. Min Range: -1.2789

Max Act: 0.9155. Min Act: -0.0000

Data Index: 414285 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 1.2789. Min Range: -1.2789

Max Act: 1.0259. Min Act: -0.0000

Data Index: 392128 (C4 (Web Text))

Max Activating Token Index: 589