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

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

Neuron 4114 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: 0.5322. Min Range: -0.5322

Max Act: 0.5108. Min Act: -0.0001

Data Index: 1196766 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5307. Min Act: -0.0001

Data Index: 323373 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.5322. Min Act: -0.0001

Data Index: 565293 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4892. Min Act: -0.0001

Data Index: 740159 (C4 (Web Text))

Max Activating Token Index: 665

Text #4

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4760. Min Act: -0.0001

Data Index: 848309 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4219. Min Act: -0.0001

Data Index: 1232138 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4536. Min Act: -0.0001

Data Index: 1322442 (C4 (Web Text))

Max Activating Token Index: 310

Text #7

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4567. Min Act: -0.0001

Data Index: 1129028 (C4 (Web Text))

Max Activating Token Index: 405

Text #8

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4801. Min Act: -0.0000

Data Index: 696141 (C4 (Web Text))

Max Activating Token Index: 290

Text #9

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4555. Min Act: -0.0001

Data Index: 284527 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4297. Min Act: -0.0001

Data Index: 1351893 (C4 (Web Text))

Max Activating Token Index: 387

Text #11

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4410. Min Act: -0.0001

Data Index: 438050 (C4 (Web Text))

Max Activating Token Index: 933

Text #12

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4251. Min Act: -0.0000

Data Index: 1225875 (C4 (Web Text))

Max Activating Token Index: 696

Text #13

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4161. Min Act: -0.0001

Data Index: 888502 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4275. Min Act: -0.0001

Data Index: 78187 (C4 (Web Text))

Max Activating Token Index: 977

Text #15

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4223. Min Act: -0.0001

Data Index: 439359 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.4120. Min Act: -0.0001

Data Index: 217784 (C4 (Web Text))

Max Activating Token Index: 563

Text #17

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3976. Min Act: -0.0001

Data Index: 1133115 (C4 (Web Text))

Max Activating Token Index: 882

Text #18

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3815. Min Act: -0.0001

Data Index: 395402 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.5322. Min Range: -0.5322

Max Act: 0.3926. Min Act: -0.0001

Data Index: 243949 (C4 (Web Text))

Max Activating Token Index: 188