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

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

Neuron 2725 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1494. Min Act: -0.0001

Data Index: 305869 (C4 (Web Text))

Max Activating Token Index: 945

Text #1

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1433. Min Act: -0.0001

Data Index: 308538 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1366. Min Act: -0.0000

Data Index: 1137449 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1123. Min Act: -0.0001

Data Index: 1553116 (Python Code)

Max Activating Token Index: 613

Text #4

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1503642 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1234. Min Act: -0.0001

Data Index: 899037 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1246. Min Act: -0.0001

Data Index: 1486902 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1228. Min Act: -0.0001

Data Index: 1639264 (Python Code)

Max Activating Token Index: 736

Text #8

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1133. Min Act: -0.0000

Data Index: 608493 (C4 (Web Text))

Max Activating Token Index: 264

Text #9

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1152. Min Act: -0.0000

Data Index: 515521 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1171. Min Act: -0.0001

Data Index: 1380282 (Python Code)

Max Activating Token Index: 876

Text #11

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1075. Min Act: -0.0001

Data Index: 791402 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1073. Min Act: 0.0000

Data Index: 873124 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1499124 (Python Code)

Max Activating Token Index: 1015

Text #14

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1370055 (Python Code)

Max Activating Token Index: 1004

Text #15

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1067. Min Act: -0.0001

Data Index: 293560 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1091. Min Act: -0.0001

Data Index: 281503 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1550122 (Python Code)

Max Activating Token Index: 691

Text #18

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1074. Min Act: -0.0001

Data Index: 435787 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 0.1494. Min Range: -0.1494

Max Act: 0.1077. Min Act: -0.0001

Data Index: 915711 (C4 (Web Text))

Max Activating Token Index: 112