Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4309 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3625. Min Act: -0.0000

Data Index: 491526 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3289. Min Act: -0.0000

Data Index: 133505 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3226. Min Act: -0.0000

Data Index: 1637174 (Python Code)

Max Activating Token Index: 539

Text #3

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3208. Min Act: -0.0000

Data Index: 984940 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3105. Min Act: 0.0000

Data Index: 242923 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.3095. Min Act: -0.0000

Data Index: 361676 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2989. Min Act: -0.0000

Data Index: 727112 (C4 (Web Text))

Max Activating Token Index: 568

Text #7

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2884. Min Act: -0.0000

Data Index: 1621812 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2642. Min Act: -0.0000

Data Index: 596902 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2816. Min Act: -0.0000

Data Index: 615528 (C4 (Web Text))

Max Activating Token Index: 182

Text #10

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2642. Min Act: -0.0000

Data Index: 473092 (C4 (Web Text))

Max Activating Token Index: 658

Text #11

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2653. Min Act: -0.0000

Data Index: 553746 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2718. Min Act: -0.0000

Data Index: 1485511 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2556. Min Act: -0.0000

Data Index: 265051 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2495. Min Act: -0.0000

Data Index: 1091797 (C4 (Web Text))

Max Activating Token Index: 462

Text #15

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2649. Min Act: -0.0000

Data Index: 1254946 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2557. Min Act: -0.0000

Data Index: 1555840 (Python Code)

Max Activating Token Index: 505

Text #17

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2504. Min Act: -0.0000

Data Index: 19885 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2498. Min Act: -0.0000

Data Index: 447397 (C4 (Web Text))

Max Activating Token Index: 855

Text #19

Max Range: 0.3625. Min Range: -0.3625

Max Act: 0.2517. Min Act: -0.0000

Data Index: 560504 (C4 (Web Text))

Max Activating Token Index: 982