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

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

Neuron 2022 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: 0.0622. Min Range: -0.0622

Max Act: 0.0618. Min Act: -0.0005

Data Index: 751459 (C4 (Web Text))

Max Activating Token Index: 690

Text #1

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0614. Min Act: -0.0006

Data Index: 297647 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0622. Min Act: -0.0006

Data Index: 486718 (C4 (Web Text))

Max Activating Token Index: 699

Text #3

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0591. Min Act: -0.0006

Data Index: 918548 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0605. Min Act: -0.0005

Data Index: 229150 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0563. Min Act: -0.0006

Data Index: 9952 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0583. Min Act: -0.0006

Data Index: 74607 (C4 (Web Text))

Max Activating Token Index: 313

Text #7

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0588. Min Act: -0.0005

Data Index: 1269698 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0553. Min Act: -0.0006

Data Index: 148493 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0561. Min Act: -0.0006

Data Index: 903070 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0571. Min Act: -0.0006

Data Index: 569719 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0526. Min Act: -0.0006

Data Index: 991725 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0568. Min Act: -0.0005

Data Index: 37706 (C4 (Web Text))

Max Activating Token Index: 306

Text #13

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0566. Min Act: -0.0006

Data Index: 943498 (C4 (Web Text))

Max Activating Token Index: 189

Text #14

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0562. Min Act: -0.0006

Data Index: 505826 (C4 (Web Text))

Max Activating Token Index: 392

Text #15

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0550. Min Act: -0.0006

Data Index: 521092 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0518. Min Act: -0.0006

Data Index: 1169841 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0539. Min Act: -0.0006

Data Index: 93499 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0547. Min Act: -0.0006

Data Index: 589390 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.0622. Min Range: -0.0622

Max Act: 0.0527. Min Act: -0.0006

Data Index: 817175 (C4 (Web Text))

Max Activating Token Index: 348