Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 160 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1985. Min Act: -0.0006

Data Index: 314329 (C4 (Web Text))

Max Activating Token Index: 513

Text #1

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1740. Min Act: -0.0006

Data Index: 1273916 (C4 (Web Text))

Max Activating Token Index: 283

Text #2

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1660. Min Act: -0.0005

Data Index: 440942 (C4 (Web Text))

Max Activating Token Index: 602

Text #3

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1692. Min Act: -0.0006

Data Index: 1174888 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1681. Min Act: -0.0006

Data Index: 1188234 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1561. Min Act: -0.0006

Data Index: 63649 (C4 (Web Text))

Max Activating Token Index: 614

Text #6

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1549. Min Act: -0.0006

Data Index: 399209 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1550. Min Act: -0.0006

Data Index: 1287449 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1528. Min Act: -0.0006

Data Index: 647220 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1507. Min Act: -0.0006

Data Index: 310311 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1547. Min Act: -0.0006

Data Index: 319815 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1546. Min Act: -0.0006

Data Index: 377577 (C4 (Web Text))

Max Activating Token Index: 1005

Text #12

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1537. Min Act: -0.0006

Data Index: 130113 (C4 (Web Text))

Max Activating Token Index: 661

Text #13

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1530. Min Act: -0.0005

Data Index: 57644 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1514. Min Act: -0.0006

Data Index: 731783 (C4 (Web Text))

Max Activating Token Index: 617

Text #15

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1511. Min Act: -0.0006

Data Index: 525317 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1439. Min Act: -0.0006

Data Index: 728451 (C4 (Web Text))

Max Activating Token Index: 514

Text #17

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1487. Min Act: -0.0006

Data Index: 391214 (C4 (Web Text))

Max Activating Token Index: 470

Text #18

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1483. Min Act: -0.0006

Data Index: 636166 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.1985. Min Range: -0.1985

Max Act: 0.1488. Min Act: -0.0006

Data Index: 897837 (C4 (Web Text))

Max Activating Token Index: 922