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

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

Neuron 1283 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1113. Min Act: -0.0002

Data Index: 786476 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1025. Min Act: -0.0002

Data Index: 224263 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1002. Min Act: -0.0002

Data Index: 1012091 (C4 (Web Text))

Max Activating Token Index: 588

Text #3

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0972. Min Act: -0.0002

Data Index: 520628 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1013. Min Act: -0.0002

Data Index: 335068 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1218487 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1006. Min Act: -0.0002

Data Index: 282556 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0977. Min Act: -0.0002

Data Index: 855164 (C4 (Web Text))

Max Activating Token Index: 331

Text #8

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0972. Min Act: -0.0002

Data Index: 615203 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1057. Min Act: -0.0002

Data Index: 166453 (C4 (Web Text))

Max Activating Token Index: 720

Text #10

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0976. Min Act: -0.0002

Data Index: 791151 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0972. Min Act: -0.0002

Data Index: 131462 (C4 (Web Text))

Max Activating Token Index: 246

Text #12

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0945. Min Act: -0.0002

Data Index: 35753 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1002. Min Act: -0.0002

Data Index: 832672 (C4 (Web Text))

Max Activating Token Index: 893

Text #14

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1070188 (C4 (Web Text))

Max Activating Token Index: 754

Text #15

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1009113 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0907. Min Act: -0.0002

Data Index: 658531 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0919. Min Act: -0.0002

Data Index: 476551 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0945. Min Act: -0.0002

Data Index: 79602 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0933. Min Act: -0.0002

Data Index: 636253 (C4 (Web Text))

Max Activating Token Index: 430