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

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

Neuron 4103 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.5003. Min Act: -0.0003

Data Index: 727087 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4445. Min Act: -0.0002

Data Index: 747440 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4174. Min Act: -0.0003

Data Index: 749227 (C4 (Web Text))

Max Activating Token Index: 595

Text #3

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4158. Min Act: -0.0002

Data Index: 504475 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4134. Min Act: -0.0002

Data Index: 1318296 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4231. Min Act: -0.0002

Data Index: 329282 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4140. Min Act: -0.0003

Data Index: 554224 (C4 (Web Text))

Max Activating Token Index: 218

Text #7

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4014. Min Act: -0.0003

Data Index: 604801 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4012. Min Act: -0.0003

Data Index: 5527 (C4 (Web Text))

Max Activating Token Index: 4

Text #9

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.4085. Min Act: -0.0002

Data Index: 1201996 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3949. Min Act: -0.0003

Data Index: 1080164 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3813. Min Act: -0.0003

Data Index: 524197 (C4 (Web Text))

Max Activating Token Index: 601

Text #12

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3914. Min Act: -0.0003

Data Index: 618693 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3746. Min Act: -0.0003

Data Index: 636679 (C4 (Web Text))

Max Activating Token Index: 29

Text #14

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3756. Min Act: -0.0003

Data Index: 1041890 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3834. Min Act: -0.0003

Data Index: 47366 (C4 (Web Text))

Max Activating Token Index: 267

Text #16

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3964. Min Act: -0.0003

Data Index: 1263905 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3950. Min Act: -0.0003

Data Index: 471535 (C4 (Web Text))

Max Activating Token Index: 106

Text #18

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3710. Min Act: -0.0003

Data Index: 338323 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.5003. Min Range: -0.5003

Max Act: 0.3819. Min Act: -0.0003

Data Index: 62737 (C4 (Web Text))

Max Activating Token Index: 455