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

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

Neuron 1416 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5236. Min Act: -0.0001

Data Index: 867251 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5244. Min Act: -0.0001

Data Index: 998483 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5540. Min Act: -0.0001

Data Index: 799703 (C4 (Web Text))

Max Activating Token Index: 242

Text #3

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5282. Min Act: -0.0001

Data Index: 698755 (C4 (Web Text))

Max Activating Token Index: 548

Text #4

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5065. Min Act: -0.0001

Data Index: 1045398 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5133. Min Act: -0.0001

Data Index: 1148604 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4795. Min Act: -0.0001

Data Index: 1240931 (C4 (Web Text))

Max Activating Token Index: 303

Text #7

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5016. Min Act: -0.0001

Data Index: 496791 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5267. Min Act: -0.0001

Data Index: 582071 (C4 (Web Text))

Max Activating Token Index: 951

Text #9

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4939. Min Act: -0.0001

Data Index: 623326 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5320. Min Act: -0.0001

Data Index: 973265 (C4 (Web Text))

Max Activating Token Index: 403

Text #11

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5419. Min Act: -0.0001

Data Index: 7171 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5427. Min Act: -0.0001

Data Index: 30616 (C4 (Web Text))

Max Activating Token Index: 671

Text #13

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5061. Min Act: -0.0001

Data Index: 793127 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.5091. Min Act: -0.0001

Data Index: 577070 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4850. Min Act: -0.0001

Data Index: 526979 (C4 (Web Text))

Max Activating Token Index: 615

Text #16

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4907. Min Act: -0.0001

Data Index: 1306537 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1198221 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4761. Min Act: -0.0001

Data Index: 1049113 (C4 (Web Text))

Max Activating Token Index: 777

Text #19

Max Range: 0.5540. Min Range: -0.5540

Max Act: 0.4691. Min Act: -0.0001

Data Index: 726945 (C4 (Web Text))

Max Activating Token Index: 522