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

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

Neuron 1232 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1638. Min Act: -0.0001

Data Index: 498933 (C4 (Web Text))

Max Activating Token Index: 862

Text #1

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1674. Min Act: -0.0001

Data Index: 864238 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1721. Min Act: -0.0001

Data Index: 601997 (C4 (Web Text))

Max Activating Token Index: 989

Text #3

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1581. Min Act: -0.0001

Data Index: 740319 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1573. Min Act: -0.0001

Data Index: 110435 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1569. Min Act: -0.0001

Data Index: 866384 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1307425 (C4 (Web Text))

Max Activating Token Index: 715

Text #7

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1595. Min Act: -0.0001

Data Index: 279391 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1476. Min Act: -0.0001

Data Index: 44015 (C4 (Web Text))

Max Activating Token Index: 860

Text #9

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1518. Min Act: -0.0001

Data Index: 607484 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1520. Min Act: -0.0001

Data Index: 562545 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1735. Min Act: -0.0001

Data Index: 439561 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1149816 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1554. Min Act: -0.0001

Data Index: 678786 (C4 (Web Text))

Max Activating Token Index: 703

Text #14

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1541. Min Act: -0.0001

Data Index: 336305 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1693. Min Act: -0.0001

Data Index: 76391 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1425. Min Act: -0.0001

Data Index: 789351 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1475. Min Act: -0.0001

Data Index: 801566 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1490. Min Act: -0.0001

Data Index: 527131 (C4 (Web Text))

Max Activating Token Index: 23

Text #19

Max Range: 0.1735. Min Range: -0.1735

Max Act: 0.1461. Min Act: -0.0001

Data Index: 595111 (C4 (Web Text))

Max Activating Token Index: 503