Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2217 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0590. Min Act: -0.0000

Data Index: 62047 (C4 (Web Text))

Max Activating Token Index: 1020

Text #1

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1590466 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0551. Min Act: -0.0000

Data Index: 1335315 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0551. Min Act: -0.0000

Data Index: 788199 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0529. Min Act: -0.0000

Data Index: 285647 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0508. Min Act: -0.0000

Data Index: 1063688 (C4 (Web Text))

Max Activating Token Index: 349

Text #6

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0566. Min Act: -0.0000

Data Index: 1611043 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0514. Min Act: -0.0000

Data Index: 725473 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0522. Min Act: -0.0000

Data Index: 545626 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0523. Min Act: -0.0000

Data Index: 281950 (C4 (Web Text))

Max Activating Token Index: 944

Text #10

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0507. Min Act: -0.0000

Data Index: 870766 (C4 (Web Text))

Max Activating Token Index: 953

Text #11

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0528. Min Act: -0.0000

Data Index: 189723 (C4 (Web Text))

Max Activating Token Index: 881

Text #12

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0472. Min Act: -0.0000

Data Index: 1360967 (Python Code)

Max Activating Token Index: 172

Text #13

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0497. Min Act: -0.0000

Data Index: 136693 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0515. Min Act: -0.0000

Data Index: 1181795 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0491. Min Act: -0.0000

Data Index: 46357 (C4 (Web Text))

Max Activating Token Index: 727

Text #16

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0465. Min Act: -0.0000

Data Index: 58972 (C4 (Web Text))

Max Activating Token Index: 551

Text #17

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0551. Min Act: -0.0000

Data Index: 380752 (C4 (Web Text))

Max Activating Token Index: 163

Text #18

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1479326 (Python Code)

Max Activating Token Index: 311

Text #19

Max Range: 0.0590. Min Range: -0.0590

Max Act: 0.0484. Min Act: -0.0000

Data Index: 369 (C4 (Web Text))

Max Activating Token Index: 395