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

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

Neuron 15 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.7644. Min Act: -0.0000

Data Index: 1049262 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.7123. Min Act: -0.0000

Data Index: 592522 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6890. Min Act: -0.0000

Data Index: 642795 (C4 (Web Text))

Max Activating Token Index: 396

Text #3

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6681. Min Act: -0.0000

Data Index: 742615 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6375. Min Act: -0.0000

Data Index: 1188942 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6450. Min Act: -0.0000

Data Index: 1152510 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6089. Min Act: -0.0000

Data Index: 648097 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5816. Min Act: 0.0000

Data Index: 735194 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6680. Min Act: -0.0000

Data Index: 1053445 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.6046. Min Act: -0.0000

Data Index: 1219166 (C4 (Web Text))

Max Activating Token Index: 818

Text #10

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5856. Min Act: -0.0000

Data Index: 781141 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.5145. Min Act: -0.0000

Data Index: 115550 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4824. Min Act: -0.0000

Data Index: 287449 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4877. Min Act: -0.0000

Data Index: 309573 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4697. Min Act: -0.0000

Data Index: 1124919 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4943. Min Act: -0.0000

Data Index: 495605 (C4 (Web Text))

Max Activating Token Index: 340

Text #16

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4581. Min Act: -0.0000

Data Index: 1187651 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4569. Min Act: -0.0000

Data Index: 582220 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1154294 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 0.7644. Min Range: -0.7644

Max Act: 0.4700. Min Act: -0.0000

Data Index: 636027 (C4 (Web Text))

Max Activating Token Index: 583