Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2680 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 2.0643. Min Range: -2.0643

Max Act: 2.0643. Min Act: -0.0001

Data Index: 933314 (C4 (Web Text))

Max Activating Token Index: 965

Text #1

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.8809. Min Act: -0.0001

Data Index: 42276 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.8929. Min Act: -0.0000

Data Index: 1283889 (C4 (Web Text))

Max Activating Token Index: 779

Text #3

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.8581. Min Act: -0.0000

Data Index: 1188372 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.9492. Min Act: -0.0001

Data Index: 176121 (C4 (Web Text))

Max Activating Token Index: 867

Text #5

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.8706. Min Act: -0.0001

Data Index: 6899 (C4 (Web Text))

Max Activating Token Index: 714

Text #6

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.8016. Min Act: -0.0001

Data Index: 235701 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.7382. Min Act: -0.0001

Data Index: 6889 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.7186. Min Act: -0.0001

Data Index: 139418 (C4 (Web Text))

Max Activating Token Index: 44

Text #9

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.6602. Min Act: -0.0000

Data Index: 433322 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.6452. Min Act: -0.0001

Data Index: 777316 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.6658. Min Act: -0.0001

Data Index: 262912 (C4 (Web Text))

Max Activating Token Index: 1010

Text #12

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.6414. Min Act: -0.0001

Data Index: 891011 (C4 (Web Text))

Max Activating Token Index: 996

Text #13

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.5865. Min Act: -0.0001

Data Index: 1346575 (C4 (Web Text))

Max Activating Token Index: 781

Text #14

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.5357. Min Act: -0.0000

Data Index: 638798 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.5388. Min Act: -0.0001

Data Index: 264948 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.5374. Min Act: -0.0001

Data Index: 852866 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.6130. Min Act: -0.0001

Data Index: 934633 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.5632. Min Act: -0.0000

Data Index: 421531 (C4 (Web Text))

Max Activating Token Index: 461

Text #19

Max Range: 2.0643. Min Range: -2.0643

Max Act: 1.5412. Min Act: -0.0001

Data Index: 1085426 (C4 (Web Text))

Max Activating Token Index: 1019