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

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

Neuron 880 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.9145. Min Act: -0.0000

Data Index: 455452 (C4 (Web Text))

Max Activating Token Index: 1008

Text #1

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1011897 (C4 (Web Text))

Max Activating Token Index: 90

Text #2

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.8259. Min Act: -0.0000

Data Index: 252254 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7493. Min Act: -0.0000

Data Index: 832606 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7691. Min Act: -0.0000

Data Index: 646236 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7326. Min Act: -0.0000

Data Index: 480983 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.7477. Min Act: -0.0000

Data Index: 607666 (C4 (Web Text))

Max Activating Token Index: 943

Text #7

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5782. Min Act: -0.0000

Data Index: 273505 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1281449 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1268229 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5410. Min Act: -0.0000

Data Index: 257152 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5453. Min Act: -0.0000

Data Index: 128585 (C4 (Web Text))

Max Activating Token Index: 77

Text #12

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5415. Min Act: -0.0000

Data Index: 1273702 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.4785. Min Act: -0.0000

Data Index: 928286 (C4 (Web Text))

Max Activating Token Index: 161

Text #14

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.5017. Min Act: -0.0000

Data Index: 542317 (C4 (Web Text))

Max Activating Token Index: 52

Text #15

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.4991. Min Act: -0.0000

Data Index: 440880 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.4643. Min Act: -0.0000

Data Index: 877758 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.4265. Min Act: -0.0000

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1027732 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.9145. Min Range: -0.9145

Max Act: 0.4131. Min Act: -0.0000

Data Index: 1202536 (C4 (Web Text))

Max Activating Token Index: 421