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

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

Neuron 1263 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: 2.4972. Min Range: -2.4972

Max Act: 2.4972. Min Act: -0.0000

Data Index: 336257 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.3542. Min Act: -0.0000

Data Index: 1175550 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.4220. Min Act: -0.0000

Data Index: 95686 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.3430. Min Act: -0.0000

Data Index: 617117 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.3260. Min Act: -0.0000

Data Index: 49247 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.0840. Min Act: -0.0000

Data Index: 624388 (C4 (Web Text))

Max Activating Token Index: 344

Text #6

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.0892. Min Act: -0.0000

Data Index: 1157145 (C4 (Web Text))

Max Activating Token Index: 759

Text #7

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.0943. Min Act: -0.0000

Data Index: 168137 (C4 (Web Text))

Max Activating Token Index: 235

Text #8

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.0610. Min Act: -0.0000

Data Index: 801307 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.9030. Min Act: -0.0000

Data Index: 880120 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.2124. Min Act: -0.0000

Data Index: 557476 (C4 (Web Text))

Max Activating Token Index: 775

Text #11

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.9752. Min Act: -0.0000

Data Index: 819394 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.9345. Min Act: -0.0000

Data Index: 1259856 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 2.4972. Min Range: -2.4972

Max Act: 2.0434. Min Act: -0.0000

Data Index: 1348875 (C4 (Web Text))

Max Activating Token Index: 348

Text #14

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.9281. Min Act: -0.0000

Data Index: 547600 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.9012. Min Act: -0.0000

Data Index: 351301 (C4 (Web Text))

Max Activating Token Index: 146

Text #16

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.7653. Min Act: -0.0000

Data Index: 321496 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.9700. Min Act: -0.0000

Data Index: 1044325 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.8641. Min Act: -0.0000

Data Index: 413582 (C4 (Web Text))

Max Activating Token Index: 166

Text #19

Max Range: 2.4972. Min Range: -2.4972

Max Act: 1.7568. Min Act: -0.0000

Data Index: 1235036 (C4 (Web Text))

Max Activating Token Index: 823