Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2480 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.4338. Min Act: -0.0004

Data Index: 961945 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3441. Min Act: -0.0004

Data Index: 802413 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3497. Min Act: -0.0004

Data Index: 756265 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3171. Min Act: -0.0004

Data Index: 884194 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3139. Min Act: -0.0004

Data Index: 1096823 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3045. Min Act: -0.0004

Data Index: 573348 (C4 (Web Text))

Max Activating Token Index: 787

Text #6

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3154. Min Act: -0.0004

Data Index: 136857 (C4 (Web Text))

Max Activating Token Index: 192

Text #7

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3258. Min Act: -0.0004

Data Index: 835851 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3095. Min Act: -0.0004

Data Index: 937493 (C4 (Web Text))

Max Activating Token Index: 331

Text #9

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.3103. Min Act: -0.0004

Data Index: 227371 (C4 (Web Text))

Max Activating Token Index: 168

Text #10

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2988. Min Act: -0.0004

Data Index: 441314 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2845. Min Act: -0.0004

Data Index: 195369 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2967. Min Act: -0.0004

Data Index: 535646 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2871. Min Act: -0.0004

Data Index: 1246178 (C4 (Web Text))

Max Activating Token Index: 550

Text #14

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2961. Min Act: -0.0004

Data Index: 522037 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2864. Min Act: -0.0004

Data Index: 602145 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2928. Min Act: -0.0004

Data Index: 1179034 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2868. Min Act: -0.0004

Data Index: 1051681 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2847. Min Act: -0.0004

Data Index: 950403 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 0.4338. Min Range: -0.4338

Max Act: 0.2612. Min Act: -0.0004

Data Index: 547046 (C4 (Web Text))

Max Activating Token Index: 568