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

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

Neuron 3749 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1949. Min Act: -0.0000

Data Index: 1074826 (C4 (Web Text))

Max Activating Token Index: 559

Text #1

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1895. Min Act: -0.0000

Data Index: 447926 (C4 (Web Text))

Max Activating Token Index: 984

Text #2

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1629. Min Act: -0.0001

Data Index: 217473 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1650. Min Act: -0.0000

Data Index: 476769 (C4 (Web Text))

Max Activating Token Index: 935

Text #4

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1661. Min Act: -0.0001

Data Index: 774400 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1571. Min Act: -0.0001

Data Index: 294256 (C4 (Web Text))

Max Activating Token Index: 412

Text #6

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1271075 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1608. Min Act: -0.0000

Data Index: 337160 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1658. Min Act: -0.0000

Data Index: 658737 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1588. Min Act: -0.0001

Data Index: 1316794 (C4 (Web Text))

Max Activating Token Index: 699

Text #10

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1567. Min Act: -0.0000

Data Index: 697819 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1029247 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1565. Min Act: -0.0001

Data Index: 926309 (C4 (Web Text))

Max Activating Token Index: 505

Text #13

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1159468 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1132085 (C4 (Web Text))

Max Activating Token Index: 921

Text #15

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1517. Min Act: -0.0000

Data Index: 775349 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1446. Min Act: -0.0000

Data Index: 164493 (C4 (Web Text))

Max Activating Token Index: 66

Text #17

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1500. Min Act: -0.0000

Data Index: 145707 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1462. Min Act: -0.0000

Data Index: 1048929 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 0.1949. Min Range: -0.1949

Max Act: 0.1440. Min Act: -0.0000

Data Index: 903485 (C4 (Web Text))

Max Activating Token Index: 73