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

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

Neuron 4823 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.9026. Min Range: -6.9026

Max Act: 6.9026. Min Act: -0.0000

Data Index: 77814 (C4 (Web Text))

Max Activating Token Index: 853

Text #1

Max Range: 6.9026. Min Range: -6.9026

Max Act: 6.0985. Min Act: -0.0000

Data Index: 612866 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 6.9026. Min Range: -6.9026

Max Act: 6.0016. Min Act: -0.0000

Data Index: 169934 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 6.9026. Min Range: -6.9026

Max Act: 5.6595. Min Act: -0.0000

Data Index: 22570 (C4 (Web Text))

Max Activating Token Index: 748

Text #4

Max Range: 6.9026. Min Range: -6.9026

Max Act: 5.0118. Min Act: -0.0000

Data Index: 960369 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 6.9026. Min Range: -6.9026

Max Act: 5.1693. Min Act: -0.0000

Data Index: 27135 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 6.9026. Min Range: -6.9026

Max Act: 5.4888. Min Act: -0.0000

Data Index: 600455 (C4 (Web Text))

Max Activating Token Index: 108

Text #7

Max Range: 6.9026. Min Range: -6.9026

Max Act: 5.2673. Min Act: -0.0000

Data Index: 1285207 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.6706. Min Act: -0.0000

Data Index: 1109201 (C4 (Web Text))

Max Activating Token Index: 449

Text #9

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.8687. Min Act: -0.0000

Data Index: 403071 (C4 (Web Text))

Max Activating Token Index: 198

Text #10

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.6834. Min Act: -0.0000

Data Index: 328733 (C4 (Web Text))

Max Activating Token Index: 515

Text #11

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.8508. Min Act: -0.0000

Data Index: 481378 (C4 (Web Text))

Max Activating Token Index: 206

Text #12

Max Range: 6.9026. Min Range: -6.9026

Max Act: 5.0034. Min Act: -0.0000

Data Index: 1132216 (C4 (Web Text))

Max Activating Token Index: 331

Text #13

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.8200. Min Act: -0.0000

Data Index: 687239 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.4653. Min Act: -0.0000

Data Index: 531705 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.1434. Min Act: -0.0000

Data Index: 598277 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.8137. Min Act: -0.0000

Data Index: 1195262 (C4 (Web Text))

Max Activating Token Index: 767

Text #17

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.2573. Min Act: -0.0000

Data Index: 572299 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.2409. Min Act: -0.0000

Data Index: 105973 (C4 (Web Text))

Max Activating Token Index: 299

Text #19

Max Range: 6.9026. Min Range: -6.9026

Max Act: 4.3747. Min Act: -0.0000

Data Index: 1089108 (C4 (Web Text))

Max Activating Token Index: 794