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

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

Neuron 1634 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7658. Min Act: -0.0001

Data Index: 1338083 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8044. Min Act: -0.0001

Data Index: 1234828 (C4 (Web Text))

Max Activating Token Index: 452

Text #2

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8380. Min Act: -0.0001

Data Index: 22281 (C4 (Web Text))

Max Activating Token Index: 356

Text #3

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8080. Min Act: -0.0001

Data Index: 542434 (C4 (Web Text))

Max Activating Token Index: 298

Text #4

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1221369 (C4 (Web Text))

Max Activating Token Index: 343

Text #5

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.8298. Min Act: -0.0001

Data Index: 496026 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.7390. Min Act: -0.0001

Data Index: 494891 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5727. Min Act: -0.0001

Data Index: 889629 (C4 (Web Text))

Max Activating Token Index: 175

Text #8

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6651. Min Act: -0.0001

Data Index: 501448 (C4 (Web Text))

Max Activating Token Index: 80

Text #9

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6586. Min Act: -0.0001

Data Index: 244942 (C4 (Web Text))

Max Activating Token Index: 869

Text #10

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6558. Min Act: -0.0001

Data Index: 391997 (C4 (Web Text))

Max Activating Token Index: 236

Text #11

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6280. Min Act: -0.0001

Data Index: 106048 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1267536 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6868. Min Act: -0.0001

Data Index: 1288769 (C4 (Web Text))

Max Activating Token Index: 475

Text #14

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6050. Min Act: -0.0001

Data Index: 701654 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6227. Min Act: -0.0001

Data Index: 220410 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6337. Min Act: -0.0001

Data Index: 846762 (C4 (Web Text))

Max Activating Token Index: 385

Text #17

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.6254. Min Act: -0.0001

Data Index: 312327 (C4 (Web Text))

Max Activating Token Index: 539

Text #18

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5481. Min Act: -0.0001

Data Index: 80344 (C4 (Web Text))

Max Activating Token Index: 355

Text #19

Max Range: 0.8380. Min Range: -0.8380

Max Act: 0.5808. Min Act: -0.0001

Data Index: 754487 (C4 (Web Text))

Max Activating Token Index: 503