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

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

Neuron 218 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: 0.1987. Min Range: -0.1987

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1311823 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1839. Min Act: -0.0001

Data Index: 1163313 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1304399 (C4 (Web Text))

Max Activating Token Index: 708

Text #3

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1649. Min Act: -0.0001

Data Index: 868408 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1604. Min Act: -0.0001

Data Index: 573650 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1571. Min Act: -0.0001

Data Index: 774322 (C4 (Web Text))

Max Activating Token Index: 965

Text #6

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1084832 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1607. Min Act: -0.0001

Data Index: 342059 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1544. Min Act: -0.0001

Data Index: 691993 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1591. Min Act: -0.0001

Data Index: 480021 (C4 (Web Text))

Max Activating Token Index: 466

Text #10

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1052357 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1511. Min Act: -0.0000

Data Index: 13633 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1412. Min Act: -0.0001

Data Index: 536126 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1561. Min Act: -0.0001

Data Index: 581730 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1102889 (C4 (Web Text))

Max Activating Token Index: 685

Text #15

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1484. Min Act: -0.0001

Data Index: 834436 (C4 (Web Text))

Max Activating Token Index: 645

Text #16

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1515. Min Act: -0.0001

Data Index: 170224 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1457. Min Act: -0.0001

Data Index: 440657 (C4 (Web Text))

Max Activating Token Index: 989

Text #18

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1505. Min Act: -0.0001

Data Index: 76649 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1987. Min Range: -0.1987

Max Act: 0.1454. Min Act: -0.0001

Data Index: 929141 (C4 (Web Text))

Max Activating Token Index: 776