Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1020 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1117397 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0993. Min Act: -0.0001

Data Index: 232327 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.1051. Min Act: -0.0000

Data Index: 128557 (C4 (Web Text))

Max Activating Token Index: 50

Text #3

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0925. Min Act: -0.0001

Data Index: 471120 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0993. Min Act: -0.0001

Data Index: 316703 (C4 (Web Text))

Max Activating Token Index: 702

Text #5

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0885. Min Act: -0.0001

Data Index: 620119 (C4 (Web Text))

Max Activating Token Index: 363

Text #6

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1022933 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1102488 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1060736 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0872. Min Act: -0.0000

Data Index: 534079 (C4 (Web Text))

Max Activating Token Index: 331

Text #10

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0904. Min Act: -0.0000

Data Index: 295766 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0909. Min Act: -0.0000

Data Index: 799361 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0851. Min Act: -0.0001

Data Index: 467254 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1131424 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0874. Min Act: -0.0000

Data Index: 761263 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0873. Min Act: -0.0000

Data Index: 437045 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0854. Min Act: -0.0000

Data Index: 510968 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0752. Min Act: -0.0000

Data Index: 1311126 (C4 (Web Text))

Max Activating Token Index: 275

Text #18

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0842. Min Act: -0.0001

Data Index: 873774 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 0.1075. Min Range: -0.1075

Max Act: 0.0840. Min Act: -0.0001

Data Index: 276539 (C4 (Web Text))

Max Activating Token Index: 60