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

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

Neuron 616 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4520. Min Act: -0.0001

Data Index: 1089743 (C4 (Web Text))

Max Activating Token Index: 689

Text #1

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4559. Min Act: -0.0001

Data Index: 640849 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4166. Min Act: -0.0001

Data Index: 953692 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4269. Min Act: -0.0001

Data Index: 928755 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4179. Min Act: -0.0001

Data Index: 123584 (C4 (Web Text))

Max Activating Token Index: 953

Text #5

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3962. Min Act: -0.0001

Data Index: 1000407 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3761. Min Act: -0.0001

Data Index: 867438 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3821. Min Act: -0.0001

Data Index: 328444 (C4 (Web Text))

Max Activating Token Index: 871

Text #8

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.4013. Min Act: -0.0001

Data Index: 453637 (C4 (Web Text))

Max Activating Token Index: 993

Text #9

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3215. Min Act: -0.0001

Data Index: 356190 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3800. Min Act: -0.0001

Data Index: 199572 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3738. Min Act: -0.0001

Data Index: 66298 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3559. Min Act: -0.0001

Data Index: 489375 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3420. Min Act: -0.0001

Data Index: 764997 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3878. Min Act: -0.0001

Data Index: 1334539 (C4 (Web Text))

Max Activating Token Index: 554

Text #15

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3800. Min Act: -0.0001

Data Index: 274496 (C4 (Web Text))

Max Activating Token Index: 274

Text #16

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3320. Min Act: -0.0001

Data Index: 1318667 (C4 (Web Text))

Max Activating Token Index: 839

Text #17

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3339. Min Act: -0.0001

Data Index: 357462 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3452. Min Act: -0.0001

Data Index: 555022 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.4559. Min Range: -0.4559

Max Act: 0.3329. Min Act: -0.0001

Data Index: 1559653 (Python Code)

Max Activating Token Index: 816