Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 4041 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0606. Min Act: -0.0003

Data Index: 1370564 (Python Code)

Max Activating Token Index: 916

Text #1

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1540400 (Python Code)

Max Activating Token Index: 641

Text #2

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0546. Min Act: -0.0003

Data Index: 965953 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1539390 (Python Code)

Max Activating Token Index: 501

Text #4

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0505. Min Act: -0.0004

Data Index: 1407666 (Python Code)

Max Activating Token Index: 741

Text #5

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0485. Min Act: -0.0004

Data Index: 1571361 (Python Code)

Max Activating Token Index: 882

Text #6

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0455. Min Act: -0.0003

Data Index: 378246 (C4 (Web Text))

Max Activating Token Index: 933

Text #7

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1569393 (Python Code)

Max Activating Token Index: 489

Text #8

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0480. Min Act: -0.0003

Data Index: 211718 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0475. Min Act: -0.0003

Data Index: 10966 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0477. Min Act: -0.0003

Data Index: 621085 (C4 (Web Text))

Max Activating Token Index: 962

Text #11

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0398. Min Act: -0.0003

Data Index: 14267 (C4 (Web Text))

Max Activating Token Index: 905

Text #12

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1043808 (C4 (Web Text))

Max Activating Token Index: 479

Text #13

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0501. Min Act: -0.0003

Data Index: 591895 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0477. Min Act: -0.0003

Data Index: 1222398 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0467. Min Act: -0.0003

Data Index: 463107 (C4 (Web Text))

Max Activating Token Index: 455

Text #16

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0493. Min Act: -0.0003

Data Index: 1041235 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0470. Min Act: -0.0003

Data Index: 589829 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1213740 (C4 (Web Text))

Max Activating Token Index: 832

Text #19

Max Range: 0.0606. Min Range: -0.0606

Max Act: 0.0482. Min Act: -0.0003

Data Index: 225768 (C4 (Web Text))

Max Activating Token Index: 984