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

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

Neuron 2760 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: 5.5991. Min Range: -5.5991

Max Act: 4.9301. Min Act: -0.0001

Data Index: 43531 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 5.5991. Min Range: -5.5991

Max Act: 5.5991. Min Act: -0.0000

Data Index: 977358 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.5820. Min Act: -0.0000

Data Index: 1153789 (C4 (Web Text))

Max Activating Token Index: 462

Text #3

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.1764. Min Act: -0.0001

Data Index: 493955 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.5225. Min Act: -0.0001

Data Index: 435552 (C4 (Web Text))

Max Activating Token Index: 64

Text #5

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.7592. Min Act: -0.0001

Data Index: 1140185 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.0761. Min Act: -0.0001

Data Index: 672254 (C4 (Web Text))

Max Activating Token Index: 179

Text #7

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.3992. Min Act: -0.0000

Data Index: 195325 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.3874. Min Act: -0.0000

Data Index: 609029 (C4 (Web Text))

Max Activating Token Index: 297

Text #9

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.3513. Min Act: -0.0001

Data Index: 1132482 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.1498. Min Act: -0.0001

Data Index: 1099651 (C4 (Web Text))

Max Activating Token Index: 735

Text #11

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.7745. Min Act: -0.0001

Data Index: 568356 (C4 (Web Text))

Max Activating Token Index: 585

Text #12

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.9462. Min Act: -0.0000

Data Index: 197141 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.6777. Min Act: -0.0001

Data Index: 993839 (C4 (Web Text))

Max Activating Token Index: 770

Text #14

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.2039. Min Act: -0.0000

Data Index: 984548 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.8013. Min Act: -0.0001

Data Index: 302232 (C4 (Web Text))

Max Activating Token Index: 410

Text #16

Max Range: 5.5991. Min Range: -5.5991

Max Act: 4.1186. Min Act: -0.0000

Data Index: 316138 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.9434. Min Act: -0.0001

Data Index: 826046 (C4 (Web Text))

Max Activating Token Index: 185

Text #18

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.9094. Min Act: -0.0001

Data Index: 868012 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 5.5991. Min Range: -5.5991

Max Act: 3.7136. Min Act: -0.0000

Data Index: 601293 (C4 (Web Text))

Max Activating Token Index: 964