Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1640 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1165323 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1211660 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0703. Min Act: -0.0002

Data Index: 1189933 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0640. Min Act: -0.0001

Data Index: 934411 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0678. Min Act: -0.0001

Data Index: 903820 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0573. Min Act: -0.0001

Data Index: 339518 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0520. Min Act: -0.0002

Data Index: 358088 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0609. Min Act: -0.0001

Data Index: 740753 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0591. Min Act: -0.0001

Data Index: 7059 (C4 (Web Text))

Max Activating Token Index: 72

Text #9

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0608. Min Act: -0.0001

Data Index: 1186232 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0567. Min Act: -0.0002

Data Index: 5626 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0575. Min Act: -0.0001

Data Index: 223826 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0606. Min Act: -0.0001

Data Index: 214137 (C4 (Web Text))

Max Activating Token Index: 607

Text #13

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0587. Min Act: -0.0001

Data Index: 644242 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0551. Min Act: -0.0001

Data Index: 819061 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0569. Min Act: -0.0001

Data Index: 1024301 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0584. Min Act: -0.0001

Data Index: 1276858 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0577. Min Act: -0.0002

Data Index: 108339 (C4 (Web Text))

Max Activating Token Index: 896

Text #18

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0549. Min Act: -0.0001

Data Index: 425055 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0763. Min Range: -0.0763

Max Act: 0.0586. Min Act: -0.0001

Data Index: 369150 (C4 (Web Text))

Max Activating Token Index: 138