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

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

Neuron 2299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.3315. Min Act: -0.0000

Data Index: 449346 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2234. Min Act: -0.0000

Data Index: 660117 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2618. Min Act: -0.0000

Data Index: 624783 (C4 (Web Text))

Max Activating Token Index: 781

Text #3

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2764. Min Act: -0.0000

Data Index: 1242436 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2560. Min Act: -0.0001

Data Index: 207711 (C4 (Web Text))

Max Activating Token Index: 165

Text #5

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2211. Min Act: -0.0000

Data Index: 1170166 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2330. Min Act: -0.0000

Data Index: 195457 (C4 (Web Text))

Max Activating Token Index: 243

Text #7

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2210. Min Act: -0.0000

Data Index: 815500 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2124. Min Act: -0.0000

Data Index: 758712 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2102. Min Act: -0.0000

Data Index: 891533 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1289094 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2233. Min Act: -0.0000

Data Index: 1262674 (C4 (Web Text))

Max Activating Token Index: 539

Text #12

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1065872 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2114. Min Act: -0.0000

Data Index: 490180 (C4 (Web Text))

Max Activating Token Index: 67

Text #14

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.1881. Min Act: -0.0000

Data Index: 106678 (C4 (Web Text))

Max Activating Token Index: 914

Text #15

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1120816 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1313282 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.1993. Min Act: -0.0000

Data Index: 1007771 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1253100 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.3315. Min Range: -0.3315

Max Act: 0.1823. Min Act: -0.0000

Data Index: 1348123 (C4 (Web Text))

Max Activating Token Index: 485