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

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

Neuron 4888 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4166. Min Range: -1.4166

Max Act: 1.4166. Min Act: -0.0000

Data Index: 864920 (C4 (Web Text))

Max Activating Token Index: 571

Text #1

Max Range: 1.4166. Min Range: -1.4166

Max Act: 1.1221. Min Act: -0.0000

Data Index: 1289517 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.4166. Min Range: -1.4166

Max Act: 1.1228. Min Act: -0.0000

Data Index: 772147 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 1.4166. Min Range: -1.4166

Max Act: 1.1337. Min Act: -0.0000

Data Index: 1087782 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.9857. Min Act: -0.0000

Data Index: 473108 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.9857. Min Act: -0.0000

Data Index: 352776 (C4 (Web Text))

Max Activating Token Index: 296

Text #6

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.9724. Min Act: -0.0000

Data Index: 763600 (C4 (Web Text))

Max Activating Token Index: 794

Text #7

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1087767 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.9418. Min Act: -0.0000

Data Index: 1144885 (C4 (Web Text))

Max Activating Token Index: 384

Text #9

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.7757. Min Act: -0.0000

Data Index: 80586 (C4 (Web Text))

Max Activating Token Index: 249

Text #10

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1282861 (C4 (Web Text))

Max Activating Token Index: 784

Text #11

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.9014. Min Act: -0.0000

Data Index: 1170364 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8718. Min Act: -0.0000

Data Index: 918978 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8628. Min Act: -0.0000

Data Index: 188494 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8294. Min Act: -0.0000

Data Index: 1011305 (C4 (Web Text))

Max Activating Token Index: 550

Text #15

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8655. Min Act: -0.0000

Data Index: 788327 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8259. Min Act: -0.0000

Data Index: 1133154 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1039459 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.8252. Min Act: -0.0000

Data Index: 274255 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.4166. Min Range: -1.4166

Max Act: 0.7607. Min Act: -0.0000

Data Index: 602151 (C4 (Web Text))

Max Activating Token Index: 255