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

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

Neuron 4560 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.8862. Min Act: -0.0000

Data Index: 1103727 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.7808. Min Act: -0.0000

Data Index: 209304 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1191869 (C4 (Web Text))

Max Activating Token Index: 507

Text #3

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6700. Min Act: -0.0000

Data Index: 379373 (C4 (Web Text))

Max Activating Token Index: 990

Text #4

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6344. Min Act: -0.0000

Data Index: 474833 (C4 (Web Text))

Max Activating Token Index: 902

Text #5

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6462. Min Act: -0.0000

Data Index: 1311652 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1083289 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6245. Min Act: -0.0000

Data Index: 89701 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6141. Min Act: -0.0000

Data Index: 1297929 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6398. Min Act: -0.0000

Data Index: 64127 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6169. Min Act: -0.0000

Data Index: 1144812 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6287. Min Act: -0.0000

Data Index: 694569 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6276. Min Act: -0.0000

Data Index: 12638 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6094. Min Act: -0.0000

Data Index: 951253 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5815. Min Act: -0.0000

Data Index: 808717 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1225143 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5812. Min Act: -0.0000

Data Index: 304713 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5700. Min Act: -0.0000

Data Index: 599241 (C4 (Web Text))

Max Activating Token Index: 261

Text #18

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1133411 (C4 (Web Text))

Max Activating Token Index: 846

Text #19

Max Range: 0.8862. Min Range: -0.8862

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1225872 (C4 (Web Text))

Max Activating Token Index: 162