Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 601 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1532078 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0003

Data Index: 1432936 (Python Code)

Max Activating Token Index: 1018

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0597. Min Act: -0.0003

Data Index: 1479554 (Python Code)

Max Activating Token Index: 125

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1440749 (Python Code)

Max Activating Token Index: 589

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0566. Min Act: -0.0004

Data Index: 1504638 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0564. Min Act: -0.0003

Data Index: 1652119 (Python Code)

Max Activating Token Index: 628

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0562. Min Act: -0.0003

Data Index: 1414654 (Python Code)

Max Activating Token Index: 166

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0550. Min Act: -0.0003

Data Index: 1429495 (Python Code)

Max Activating Token Index: 516

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0539. Min Act: -0.0003

Data Index: 1566073 (Python Code)

Max Activating Token Index: 400

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1630115 (Python Code)

Max Activating Token Index: 479

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0520. Min Act: -0.0003

Data Index: 1495288 (Python Code)

Max Activating Token Index: 451

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1522492 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1399295 (Python Code)

Max Activating Token Index: 386

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0523. Min Act: -0.0004

Data Index: 1431209 (Python Code)

Max Activating Token Index: 413

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1580864 (Python Code)

Max Activating Token Index: 867

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0512. Min Act: -0.0003

Data Index: 1614035 (Python Code)

Max Activating Token Index: 915

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1450992 (Python Code)

Max Activating Token Index: 707

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1473341 (Python Code)

Max Activating Token Index: 206

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1484419 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0509. Min Act: -0.0003

Data Index: 1577128 (Python Code)

Max Activating Token Index: 483