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

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

Neuron 498 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1627. Min Act: -0.0002

Data Index: 810047 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0002

Data Index: 388704 (C4 (Web Text))

Max Activating Token Index: 370

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1052027 (C4 (Web Text))

Max Activating Token Index: 183

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1217. Min Act: -0.0002

Data Index: 576432 (C4 (Web Text))

Max Activating Token Index: 766

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1260. Min Act: -0.0002

Data Index: 404192 (C4 (Web Text))

Max Activating Token Index: 38

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1251. Min Act: -0.0002

Data Index: 411067 (C4 (Web Text))

Max Activating Token Index: 489

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1221. Min Act: -0.0002

Data Index: 1208001 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1220. Min Act: -0.0002

Data Index: 268519 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1161. Min Act: -0.0002

Data Index: 782306 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1127. Min Act: -0.0002

Data Index: 725065 (C4 (Web Text))

Max Activating Token Index: 554

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1043593 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1079. Min Act: -0.0002

Data Index: 46002 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0996. Min Act: -0.0002

Data Index: 1330014 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0946. Min Act: -0.0002

Data Index: 778796 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0967. Min Act: -0.0002

Data Index: 1036392 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0990. Min Act: -0.0002

Data Index: 1005192 (C4 (Web Text))

Max Activating Token Index: 97

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0935. Min Act: -0.0002

Data Index: 860511 (C4 (Web Text))

Max Activating Token Index: 183

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0926. Min Act: -0.0002

Data Index: 1160662 (C4 (Web Text))

Max Activating Token Index: 246

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0945. Min Act: -0.0002

Data Index: 81871 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.0910. Min Act: -0.0002

Data Index: 793454 (C4 (Web Text))

Max Activating Token Index: 87