Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4673 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0102. Min Act: -0.0002

Data Index: 148976 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0093. Min Act: -0.0002

Data Index: 81783 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0090. Min Act: -0.0002

Data Index: 795922 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0089. Min Act: -0.0002

Data Index: 1272423 (C4 (Web Text))

Max Activating Token Index: 544

Text #4

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0088. Min Act: -0.0002

Data Index: 699615 (C4 (Web Text))

Max Activating Token Index: 380

Text #5

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 33136 (C4 (Web Text))

Max Activating Token Index: 541

Text #6

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 566656 (C4 (Web Text))

Max Activating Token Index: 145

Text #7

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 975749 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 287358 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 903378 (C4 (Web Text))

Max Activating Token Index: 1002

Text #10

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1183644 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0002

Data Index: 237150 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0002

Data Index: 203785 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0002

Data Index: 282661 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0002

Data Index: 1218620 (C4 (Web Text))

Max Activating Token Index: 142

Text #15

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0002

Data Index: 559869 (C4 (Web Text))

Max Activating Token Index: 587

Text #16

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0087. Min Act: -0.0002

Data Index: 1155670 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0085. Min Act: -0.0002

Data Index: 543841 (C4 (Web Text))

Max Activating Token Index: 720

Text #18

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0086. Min Act: -0.0002

Data Index: 353022 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0102. Min Range: -0.0102

Max Act: 0.0084. Min Act: -0.0002

Data Index: 232521 (C4 (Web Text))

Max Activating Token Index: 30