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

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

Neuron 1324 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: 1.7853. Min Range: -1.7853

Max Act: 1.7514. Min Act: -0.0001

Data Index: 745794 (C4 (Web Text))

Max Activating Token Index: 647

Text #1

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7853. Min Act: -0.0001

Data Index: 1024646 (C4 (Web Text))

Max Activating Token Index: 841

Text #2

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6719. Min Act: -0.0001

Data Index: 995156 (C4 (Web Text))

Max Activating Token Index: 527

Text #3

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6069. Min Act: -0.0001

Data Index: 866246 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5068. Min Act: -0.0001

Data Index: 1263823 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5347. Min Act: -0.0001

Data Index: 146956 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7640. Min Act: -0.0001

Data Index: 597134 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.4315. Min Act: -0.0001

Data Index: 341498 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5139. Min Act: -0.0001

Data Index: 153132 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5588. Min Act: -0.0001

Data Index: 145731 (C4 (Web Text))

Max Activating Token Index: 906

Text #10

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6033. Min Act: -0.0001

Data Index: 344150 (C4 (Web Text))

Max Activating Token Index: 639

Text #11

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.4096. Min Act: -0.0001

Data Index: 78745 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5750. Min Act: -0.0001

Data Index: 1050354 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.7678. Min Act: -0.0001

Data Index: 32891 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.4709. Min Act: -0.0001

Data Index: 1167494 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6057. Min Act: -0.0001

Data Index: 178136 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.3198. Min Act: -0.0001

Data Index: 1224992 (C4 (Web Text))

Max Activating Token Index: 322

Text #17

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6703. Min Act: -0.0001

Data Index: 53898 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.5081. Min Act: -0.0001

Data Index: 847889 (C4 (Web Text))

Max Activating Token Index: 549

Text #19

Max Range: 1.7853. Min Range: -1.7853

Max Act: 1.6283. Min Act: -0.0001

Data Index: 1301956 (C4 (Web Text))

Max Activating Token Index: 601