Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 546 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.7187. Min Act: -0.0000

Data Index: 1452486 (Python Code)

Max Activating Token Index: 746

Text #1

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.7671. Min Act: -0.0000

Data Index: 1370082 (Python Code)

Max Activating Token Index: 563

Text #2

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.5081. Min Act: -0.0000

Data Index: 1483914 (Python Code)

Max Activating Token Index: 859

Text #3

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.2911. Min Act: -0.0000

Data Index: 662451 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.3794. Min Act: -0.0000

Data Index: 1481828 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.3102. Min Act: -0.0000

Data Index: 1511864 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.1033. Min Act: -0.0000

Data Index: 1245869 (C4 (Web Text))

Max Activating Token Index: 499

Text #7

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.2134. Min Act: -0.0000

Data Index: 1240570 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.1283. Min Act: -0.0000

Data Index: 345923 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.1374. Min Act: -0.0000

Data Index: 950753 (C4 (Web Text))

Max Activating Token Index: 457

Text #10

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.0813. Min Act: -0.0000

Data Index: 1047411 (C4 (Web Text))

Max Activating Token Index: 537

Text #11

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.9690. Min Act: -0.0000

Data Index: 1367825 (Python Code)

Max Activating Token Index: 397

Text #12

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.9196. Min Act: -0.0000

Data Index: 358788 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.8581. Min Act: -0.0000

Data Index: 1398527 (Python Code)

Max Activating Token Index: 794

Text #14

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.8238. Min Act: -0.0000

Data Index: 1438062 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.8047. Min Act: -0.0000

Data Index: 198109 (C4 (Web Text))

Max Activating Token Index: 835

Text #16

Max Range: 2.7671. Min Range: -2.7671

Max Act: 2.0144. Min Act: -0.0000

Data Index: 263936 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.8798. Min Act: -0.0000

Data Index: 626221 (C4 (Web Text))

Max Activating Token Index: 600

Text #18

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.8767. Min Act: -0.0000

Data Index: 1581525 (Python Code)

Max Activating Token Index: 350

Text #19

Max Range: 2.7671. Min Range: -2.7671

Max Act: 1.9620. Min Act: -0.0000

Data Index: 1522052 (Python Code)

Max Activating Token Index: 411