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

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

Neuron 3748 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.6237. Min Act: -0.0001

Data Index: 927534 (C4 (Web Text))

Max Activating Token Index: 422

Text #1

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.5861. Min Act: -0.0001

Data Index: 914258 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.3831. Min Act: -0.0001

Data Index: 1098526 (C4 (Web Text))

Max Activating Token Index: 547

Text #3

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.4078. Min Act: -0.0001

Data Index: 1018640 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2668. Min Act: -0.0001

Data Index: 583282 (C4 (Web Text))

Max Activating Token Index: 625

Text #5

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2871. Min Act: -0.0001

Data Index: 156308 (C4 (Web Text))

Max Activating Token Index: 218

Text #6

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.2260. Min Act: -0.0001

Data Index: 691314 (C4 (Web Text))

Max Activating Token Index: 107

Text #7

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1985. Min Act: -0.0001

Data Index: 801306 (C4 (Web Text))

Max Activating Token Index: 693

Text #8

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1765. Min Act: -0.0001

Data Index: 1112217 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.0099. Min Act: -0.0001

Data Index: 640581 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.1232. Min Act: -0.0001

Data Index: 720648 (C4 (Web Text))

Max Activating Token Index: 10

Text #11

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.0616. Min Act: -0.0001

Data Index: 838242 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.0147. Min Act: -0.0001

Data Index: 305061 (C4 (Web Text))

Max Activating Token Index: 539

Text #13

Max Range: 1.6237. Min Range: -1.6237

Max Act: 0.9997. Min Act: -0.0001

Data Index: 796325 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 1.6237. Min Range: -1.6237

Max Act: 0.8493. Min Act: -0.0001

Data Index: 9851 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 1.6237. Min Range: -1.6237

Max Act: 0.9556. Min Act: -0.0001

Data Index: 212483 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.0487. Min Act: -0.0001

Data Index: 762328 (C4 (Web Text))

Max Activating Token Index: 176

Text #17

Max Range: 1.6237. Min Range: -1.6237

Max Act: 1.0005. Min Act: -0.0001

Data Index: 32087 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 1.6237. Min Range: -1.6237

Max Act: 0.9030. Min Act: -0.0001

Data Index: 470847 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 1.6237. Min Range: -1.6237

Max Act: 0.9359. Min Act: -0.0001

Data Index: 604713 (C4 (Web Text))

Max Activating Token Index: 601