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

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

Neuron 618 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0098. Min Act: -0.0006

Data Index: 226031 (C4 (Web Text))

Max Activating Token Index: 443

Text #1

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0093. Min Act: -0.0006

Data Index: 1630571 (Python Code)

Max Activating Token Index: 713

Text #2

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0090. Min Act: -0.0006

Data Index: 419466 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0089. Min Act: -0.0006

Data Index: 1344546 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0084. Min Act: -0.0006

Data Index: 240776 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0085. Min Act: -0.0006

Data Index: 1143896 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0082. Min Act: -0.0006

Data Index: 655016 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0081. Min Act: -0.0006

Data Index: 803797 (C4 (Web Text))

Max Activating Token Index: 402

Text #8

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 948528 (C4 (Web Text))

Max Activating Token Index: 565

Text #9

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1191306 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0080. Min Act: -0.0006

Data Index: 1170173 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 919820 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0078. Min Act: -0.0006

Data Index: 308616 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0079. Min Act: -0.0006

Data Index: 311974 (C4 (Web Text))

Max Activating Token Index: 205

Text #14

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0077. Min Act: -0.0006

Data Index: 729987 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0078. Min Act: -0.0006

Data Index: 800613 (C4 (Web Text))

Max Activating Token Index: 872

Text #16

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0075. Min Act: -0.0006

Data Index: 1204962 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0076. Min Act: -0.0006

Data Index: 195969 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0073. Min Act: -0.0006

Data Index: 540426 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.0098. Min Range: -0.0098

Max Act: 0.0077. Min Act: -0.0006

Data Index: 560731 (C4 (Web Text))

Max Activating Token Index: 1007