Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1415 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4694. Min Act: -0.0004

Data Index: 496212 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4790. Min Act: -0.0004

Data Index: 656077 (C4 (Web Text))

Max Activating Token Index: 321

Text #2

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4739. Min Act: -0.0004

Data Index: 834413 (C4 (Web Text))

Max Activating Token Index: 647

Text #3

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4585. Min Act: -0.0004

Data Index: 104926 (C4 (Web Text))

Max Activating Token Index: 467

Text #4

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4361. Min Act: -0.0004

Data Index: 786969 (C4 (Web Text))

Max Activating Token Index: 531

Text #5

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4399. Min Act: -0.0005

Data Index: 421306 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4245. Min Act: -0.0004

Data Index: 933987 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4091. Min Act: -0.0004

Data Index: 466841 (C4 (Web Text))

Max Activating Token Index: 435

Text #8

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4193. Min Act: -0.0004

Data Index: 445947 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4155. Min Act: -0.0004

Data Index: 195816 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4148. Min Act: -0.0004

Data Index: 718656 (C4 (Web Text))

Max Activating Token Index: 335

Text #11

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4140. Min Act: -0.0005

Data Index: 152760 (C4 (Web Text))

Max Activating Token Index: 701

Text #12

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3995. Min Act: -0.0004

Data Index: 915929 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4082. Min Act: -0.0004

Data Index: 974802 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4070. Min Act: -0.0004

Data Index: 623545 (C4 (Web Text))

Max Activating Token Index: 402

Text #15

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3921. Min Act: -0.0004

Data Index: 480024 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4029. Min Act: -0.0004

Data Index: 929390 (C4 (Web Text))

Max Activating Token Index: 487

Text #17

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4009. Min Act: -0.0004

Data Index: 381667 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.4010. Min Act: -0.0005

Data Index: 286798 (C4 (Web Text))

Max Activating Token Index: 790

Text #19

Max Range: 0.4790. Min Range: -0.4790

Max Act: 0.3986. Min Act: -0.0004

Data Index: 849047 (C4 (Web Text))

Max Activating Token Index: 1022