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

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

Neuron 1112 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1432845 (Python Code)

Max Activating Token Index: 607

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0699. Min Act: -0.0000

Data Index: 836920 (C4 (Web Text))

Max Activating Token Index: 906

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0655. Min Act: -0.0000

Data Index: 278302 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0651. Min Act: -0.0000

Data Index: 804507 (C4 (Web Text))

Max Activating Token Index: 722

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0558. Min Act: -0.0000

Data Index: 240876 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0569. Min Act: -0.0000

Data Index: 165906 (C4 (Web Text))

Max Activating Token Index: 958

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0514. Min Act: -0.0000

Data Index: 1368905 (Python Code)

Max Activating Token Index: 921

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0483. Min Act: -0.0000

Data Index: 699258 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0496. Min Act: -0.0000

Data Index: 1334874 (C4 (Web Text))

Max Activating Token Index: 300

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0549. Min Act: -0.0000

Data Index: 1538043 (Python Code)

Max Activating Token Index: 811

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0508. Min Act: -0.0001

Data Index: 356516 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1610259 (Python Code)

Max Activating Token Index: 529

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0431. Min Act: -0.0000

Data Index: 1580002 (Python Code)

Max Activating Token Index: 278

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0457. Min Act: -0.0000

Data Index: 628240 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1551076 (Python Code)

Max Activating Token Index: 863

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0465. Min Act: -0.0001

Data Index: 1585735 (Python Code)

Max Activating Token Index: 445

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0445. Min Act: -0.0000

Data Index: 1564613 (Python Code)

Max Activating Token Index: 248

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0464. Min Act: -0.0000

Data Index: 482510 (C4 (Web Text))

Max Activating Token Index: 633

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0468. Min Act: -0.0000

Data Index: 462874 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0431. Min Act: -0.0000

Data Index: 309065 (C4 (Web Text))

Max Activating Token Index: 608