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

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

Neuron 3191 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7569. Min Act: -0.0001

Data Index: 69014 (C4 (Web Text))

Max Activating Token Index: 280

Text #1

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7496. Min Act: -0.0001

Data Index: 1307967 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7305. Min Act: -0.0000

Data Index: 847836 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7344. Min Act: -0.0001

Data Index: 411905 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6796. Min Act: -0.0000

Data Index: 1099040 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7115. Min Act: -0.0001

Data Index: 1491562 (Python Code)

Max Activating Token Index: 425

Text #6

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7311. Min Act: -0.0001

Data Index: 1187004 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6775. Min Act: -0.0001

Data Index: 1004236 (C4 (Web Text))

Max Activating Token Index: 990

Text #8

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6691. Min Act: -0.0001

Data Index: 88750 (C4 (Web Text))

Max Activating Token Index: 192

Text #9

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1285008 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6984. Min Act: -0.0000

Data Index: 755086 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6917. Min Act: -0.0000

Data Index: 807594 (C4 (Web Text))

Max Activating Token Index: 423

Text #12

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6691. Min Act: -0.0001

Data Index: 1004546 (C4 (Web Text))

Max Activating Token Index: 884

Text #13

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6525. Min Act: -0.0000

Data Index: 833605 (C4 (Web Text))

Max Activating Token Index: 865

Text #14

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6618. Min Act: -0.0001

Data Index: 813900 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6478. Min Act: -0.0000

Data Index: 561425 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6457. Min Act: -0.0000

Data Index: 213035 (C4 (Web Text))

Max Activating Token Index: 835

Text #17

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6467. Min Act: -0.0001

Data Index: 869320 (C4 (Web Text))

Max Activating Token Index: 997

Text #18

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.6447. Min Act: -0.0000

Data Index: 446759 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.7569. Min Range: -0.7569

Max Act: 0.5976. Min Act: -0.0000

Data Index: 243262 (C4 (Web Text))

Max Activating Token Index: 791