Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1786 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1322. Min Act: -0.0002

Data Index: 128285 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1301. Min Act: -0.0002

Data Index: 815966 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1276. Min Act: -0.0002

Data Index: 1248082 (C4 (Web Text))

Max Activating Token Index: 663

Text #3

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1174. Min Act: -0.0002

Data Index: 541574 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1129. Min Act: -0.0002

Data Index: 606961 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1119. Min Act: -0.0002

Data Index: 830612 (C4 (Web Text))

Max Activating Token Index: 685

Text #6

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1188. Min Act: -0.0002

Data Index: 234337 (C4 (Web Text))

Max Activating Token Index: 514

Text #7

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1144. Min Act: -0.0002

Data Index: 471844 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1060. Min Act: -0.0002

Data Index: 909598 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1066. Min Act: -0.0002

Data Index: 63088 (C4 (Web Text))

Max Activating Token Index: 848

Text #10

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1055. Min Act: -0.0002

Data Index: 19795 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1001. Min Act: -0.0002

Data Index: 117540 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1073331 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1036. Min Act: -0.0002

Data Index: 1228072 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1009. Min Act: -0.0002

Data Index: 473121 (C4 (Web Text))

Max Activating Token Index: 511

Text #15

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1022. Min Act: -0.0002

Data Index: 178658 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1131781 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.0994. Min Act: -0.0001

Data Index: 870537 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1003. Min Act: -0.0002

Data Index: 881641 (C4 (Web Text))

Max Activating Token Index: 388

Text #19

Max Range: 0.1322. Min Range: -0.1322

Max Act: 0.1055. Min Act: -0.0002

Data Index: 735616 (C4 (Web Text))

Max Activating Token Index: 477