Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1099 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0006

Data Index: 344297 (C4 (Web Text))

Max Activating Token Index: 224

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0278. Min Act: -0.0006

Data Index: 754927 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0264. Min Act: -0.0006

Data Index: 607943 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0276. Min Act: -0.0006

Data Index: 651870 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0262. Min Act: -0.0006

Data Index: 1146202 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0272. Min Act: -0.0006

Data Index: 186734 (C4 (Web Text))

Max Activating Token Index: 599

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1159168 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0265. Min Act: -0.0006

Data Index: 206066 (C4 (Web Text))

Max Activating Token Index: 614

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0263. Min Act: -0.0006

Data Index: 1132486 (C4 (Web Text))

Max Activating Token Index: 47

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0260. Min Act: -0.0006

Data Index: 944785 (C4 (Web Text))

Max Activating Token Index: 1011

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0255. Min Act: -0.0006

Data Index: 585271 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0259. Min Act: -0.0006

Data Index: 1303313 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0268. Min Act: -0.0006

Data Index: 853807 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0251. Min Act: -0.0006

Data Index: 495139 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0249. Min Act: -0.0006

Data Index: 616955 (C4 (Web Text))

Max Activating Token Index: 623

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0250. Min Act: -0.0006

Data Index: 473864 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0255. Min Act: -0.0006

Data Index: 1066921 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0249. Min Act: -0.0006

Data Index: 268513 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0248. Min Act: -0.0006

Data Index: 517756 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0248. Min Act: -0.0006

Data Index: 557970 (C4 (Web Text))

Max Activating Token Index: 885