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

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

Neuron 9 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1045786 (C4 (Web Text))

Max Activating Token Index: 888

Text #1

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1076909 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0069. Min Act: -0.0006

Data Index: 711149 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0073. Min Act: -0.0006

Data Index: 407988 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0072. Min Act: -0.0006

Data Index: 236459 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1098384 (C4 (Web Text))

Max Activating Token Index: 621

Text #6

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0069. Min Act: -0.0006

Data Index: 899423 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0069. Min Act: -0.0006

Data Index: 36558 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0071. Min Act: -0.0006

Data Index: 118245 (C4 (Web Text))

Max Activating Token Index: 314

Text #9

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1302056 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0070. Min Act: -0.0006

Data Index: 368809 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0069. Min Act: -0.0006

Data Index: 855184 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0078. Min Act: -0.0006

Data Index: 998758 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0070. Min Act: -0.0006

Data Index: 1455934 (Python Code)

Max Activating Token Index: 426

Text #14

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0059. Min Act: -0.0006

Data Index: 944879 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0067. Min Act: -0.0006

Data Index: 1413524 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0068. Min Act: -0.0006

Data Index: 939190 (C4 (Web Text))

Max Activating Token Index: 1013

Text #17

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0067. Min Act: -0.0006

Data Index: 708364 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0068. Min Act: -0.0006

Data Index: 1373197 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0065. Min Act: -0.0006

Data Index: 808451 (C4 (Web Text))

Max Activating Token Index: 727