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

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

Neuron 647 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: 0.3039. Min Range: -0.3039

Max Act: 0.3039. Min Act: -0.0001

Data Index: 674689 (C4 (Web Text))

Max Activating Token Index: 53

Text #1

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2915. Min Act: -0.0001

Data Index: 518780 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2891. Min Act: -0.0001

Data Index: 20662 (C4 (Web Text))

Max Activating Token Index: 287

Text #3

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2633. Min Act: -0.0001

Data Index: 687731 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2635. Min Act: -0.0001

Data Index: 233702 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2479. Min Act: -0.0001

Data Index: 884218 (C4 (Web Text))

Max Activating Token Index: 532

Text #6

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2344. Min Act: -0.0001

Data Index: 620989 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2356. Min Act: -0.0001

Data Index: 74422 (C4 (Web Text))

Max Activating Token Index: 742

Text #8

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2113. Min Act: -0.0001

Data Index: 479057 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2037. Min Act: -0.0001

Data Index: 886276 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2039. Min Act: -0.0001

Data Index: 1156802 (C4 (Web Text))

Max Activating Token Index: 64

Text #11

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1992. Min Act: -0.0001

Data Index: 722308 (C4 (Web Text))

Max Activating Token Index: 124

Text #12

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1868. Min Act: -0.0001

Data Index: 441162 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1960. Min Act: -0.0001

Data Index: 558050 (C4 (Web Text))

Max Activating Token Index: 481

Text #14

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1982. Min Act: -0.0001

Data Index: 327466 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1787. Min Act: -0.0001

Data Index: 339971 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1801. Min Act: -0.0001

Data Index: 855462 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1793. Min Act: -0.0001

Data Index: 983721 (C4 (Web Text))

Max Activating Token Index: 266

Text #18

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.1944. Min Act: -0.0001

Data Index: 912580 (C4 (Web Text))

Max Activating Token Index: 146

Text #19

Max Range: 0.3039. Min Range: -0.3039

Max Act: 0.2003. Min Act: -0.0001

Data Index: 742300 (C4 (Web Text))

Max Activating Token Index: 278