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

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

Neuron 1138 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: 2.4675. Min Range: -2.4675

Max Act: 2.4675. Min Act: -0.0000

Data Index: 423417 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 2.4675. Min Range: -2.4675

Max Act: 2.2080. Min Act: -0.0000

Data Index: 392859 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.9030. Min Act: -0.0000

Data Index: 352367 (C4 (Web Text))

Max Activating Token Index: 221

Text #3

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.9628. Min Act: -0.0000

Data Index: 457691 (C4 (Web Text))

Max Activating Token Index: 264

Text #4

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.8525. Min Act: -0.0000

Data Index: 408092 (C4 (Web Text))

Max Activating Token Index: 167

Text #5

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.8953. Min Act: -0.0000

Data Index: 323470 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7939. Min Act: -0.0000

Data Index: 722009 (C4 (Web Text))

Max Activating Token Index: 134

Text #7

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7983. Min Act: -0.0000

Data Index: 1125959 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.6357. Min Act: -0.0000

Data Index: 17237 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.9816. Min Act: -0.0000

Data Index: 1651925 (Python Code)

Max Activating Token Index: 959

Text #10

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7800. Min Act: -0.0000

Data Index: 1171070 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7623. Min Act: -0.0000

Data Index: 66768 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.5662. Min Act: -0.0000

Data Index: 256715 (C4 (Web Text))

Max Activating Token Index: 738

Text #13

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7306. Min Act: -0.0000

Data Index: 773880 (C4 (Web Text))

Max Activating Token Index: 49

Text #14

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.5374. Min Act: -0.0000

Data Index: 1225914 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.6164. Min Act: -0.0000

Data Index: 937606 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.7825. Min Act: -0.0000

Data Index: 204971 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.4594. Min Act: -0.0000

Data Index: 520324 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.4505. Min Act: -0.0000

Data Index: 784347 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 2.4675. Min Range: -2.4675

Max Act: 1.6097. Min Act: -0.0000

Data Index: 62525 (C4 (Web Text))

Max Activating Token Index: 278