Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1319 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0087. Min Act: -0.0006

Data Index: 1054009 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0086. Min Act: -0.0007

Data Index: 1183179 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0085. Min Act: -0.0006

Data Index: 970168 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0006

Data Index: 61284 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0084. Min Act: -0.0006

Data Index: 67388 (C4 (Web Text))

Max Activating Token Index: 413

Text #5

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0081. Min Act: -0.0006

Data Index: 1052579 (C4 (Web Text))

Max Activating Token Index: 232

Text #6

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 302154 (C4 (Web Text))

Max Activating Token Index: 784

Text #7

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0078. Min Act: -0.0006

Data Index: 507733 (C4 (Web Text))

Max Activating Token Index: 769

Text #8

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0082. Min Act: -0.0006

Data Index: 752000 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0080. Min Act: -0.0005

Data Index: 1652929 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1068644 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0078. Min Act: -0.0006

Data Index: 493909 (C4 (Web Text))

Max Activating Token Index: 47

Text #12

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0079. Min Act: -0.0006

Data Index: 811946 (C4 (Web Text))

Max Activating Token Index: 389

Text #13

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0079. Min Act: -0.0006

Data Index: 1228523 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0076. Min Act: -0.0006

Data Index: 472025 (C4 (Web Text))

Max Activating Token Index: 966

Text #15

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0078. Min Act: -0.0006

Data Index: 607076 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0076. Min Act: -0.0005

Data Index: 1438906 (Python Code)

Max Activating Token Index: 940

Text #17

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 748556 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0006

Data Index: 45733 (C4 (Web Text))

Max Activating Token Index: 112

Text #19

Max Range: 0.0087. Min Range: -0.0087

Max Act: 0.0077. Min Act: -0.0005

Data Index: 1632867 (Python Code)

Max Activating Token Index: 243