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

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

Neuron 763 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0005

Data Index: 775507 (C4 (Web Text))

Max Activating Token Index: 337

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0097. Min Act: -0.0005

Data Index: 1293586 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0005

Data Index: 185114 (C4 (Web Text))

Max Activating Token Index: 884

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0098. Min Act: -0.0005

Data Index: 1460 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0005

Data Index: 111076 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0091. Min Act: -0.0005

Data Index: 113970 (C4 (Web Text))

Max Activating Token Index: 548

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0095. Min Act: -0.0005

Data Index: 868832 (C4 (Web Text))

Max Activating Token Index: 506

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0089. Min Act: -0.0005

Data Index: 139254 (C4 (Web Text))

Max Activating Token Index: 609

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0094. Min Act: -0.0005

Data Index: 296855 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0005

Data Index: 331987 (C4 (Web Text))

Max Activating Token Index: 242

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0005

Data Index: 124050 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0085. Min Act: -0.0005

Data Index: 495826 (C4 (Web Text))

Max Activating Token Index: 761

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0090. Min Act: -0.0005

Data Index: 949039 (C4 (Web Text))

Max Activating Token Index: 435

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: -0.0005

Data Index: 905759 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: -0.0005

Data Index: 307404 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0005

Data Index: 356169 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0084. Min Act: -0.0005

Data Index: 1255720 (C4 (Web Text))

Max Activating Token Index: 13

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0086. Min Act: -0.0005

Data Index: 1109317 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0083. Min Act: -0.0005

Data Index: 588570 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0082. Min Act: -0.0005

Data Index: 269880 (C4 (Web Text))

Max Activating Token Index: 600