Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 890 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.5287. Min Act: -0.0000

Data Index: 976351 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.4640. Min Act: -0.0000

Data Index: 519086 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.2020. Min Act: -0.0000

Data Index: 909941 (C4 (Web Text))

Max Activating Token Index: 6

Text #3

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.2565. Min Act: -0.0000

Data Index: 1292757 (C4 (Web Text))

Max Activating Token Index: 411

Text #4

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.1036. Min Act: -0.0000

Data Index: 866726 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.1840. Min Act: -0.0000

Data Index: 361933 (C4 (Web Text))

Max Activating Token Index: 397

Text #6

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.0477. Min Act: -0.0000

Data Index: 973735 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.0964. Min Act: -0.0000

Data Index: 501359 (C4 (Web Text))

Max Activating Token Index: 335

Text #8

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.9140. Min Act: -0.0000

Data Index: 20154 (C4 (Web Text))

Max Activating Token Index: 864

Text #9

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.0378. Min Act: -0.0000

Data Index: 299696 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.1190. Min Act: -0.0000

Data Index: 1224749 (C4 (Web Text))

Max Activating Token Index: 424

Text #11

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.9161. Min Act: -0.0000

Data Index: 673756 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 2.5287. Min Range: -2.5287

Max Act: 2.1009. Min Act: -0.0000

Data Index: 476725 (C4 (Web Text))

Max Activating Token Index: 243

Text #13

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.8724. Min Act: -0.0000

Data Index: 1244819 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.8737. Min Act: -0.0000

Data Index: 808672 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.8366. Min Act: -0.0000

Data Index: 246033 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.9286. Min Act: -0.0000

Data Index: 905204 (C4 (Web Text))

Max Activating Token Index: 593

Text #17

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.7986. Min Act: -0.0000

Data Index: 727831 (C4 (Web Text))

Max Activating Token Index: 994

Text #18

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.6010. Min Act: -0.0000

Data Index: 435459 (C4 (Web Text))

Max Activating Token Index: 792

Text #19

Max Range: 2.5287. Min Range: -2.5287

Max Act: 1.8882. Min Act: -0.0000

Data Index: 927395 (C4 (Web Text))

Max Activating Token Index: 1022