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

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

Neuron 4872 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.6776. Min Act: -0.0000

Data Index: 1259348 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.0787. Min Act: -0.0000

Data Index: 705753 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 3.6776. Min Range: -3.6776

Max Act: 3.0257. Min Act: -0.0000

Data Index: 1100473 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.7096. Min Act: -0.0000

Data Index: 298125 (C4 (Web Text))

Max Activating Token Index: 683

Text #4

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.9383. Min Act: -0.0000

Data Index: 496518 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.7273. Min Act: -0.0000

Data Index: 297001 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 3.6776. Min Range: -3.6776

Max Act: 2.4659. Min Act: -0.0000

Data Index: 625726 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.8439. Min Act: -0.0000

Data Index: 371562 (C4 (Web Text))

Max Activating Token Index: 540

Text #8

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.7588. Min Act: -0.0000

Data Index: 1483653 (Python Code)

Max Activating Token Index: 828

Text #9

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.7586. Min Act: -0.0000

Data Index: 1652922 (Python Code)

Max Activating Token Index: 552

Text #10

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.8300. Min Act: -0.0000

Data Index: 1402678 (Python Code)

Max Activating Token Index: 684

Text #11

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.6421. Min Act: -0.0000

Data Index: 627083 (C4 (Web Text))

Max Activating Token Index: 646

Text #12

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.6621. Min Act: -0.0000

Data Index: 1524978 (Python Code)

Max Activating Token Index: 777

Text #13

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.6836. Min Act: -0.0000

Data Index: 1371905 (Python Code)

Max Activating Token Index: 931

Text #14

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.6178. Min Act: -0.0000

Data Index: 1634075 (Python Code)

Max Activating Token Index: 542

Text #15

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1619958 (Python Code)

Max Activating Token Index: 373

Text #16

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.6242. Min Act: -0.0000

Data Index: 1449784 (Python Code)

Max Activating Token Index: 586

Text #17

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.6415. Min Act: -0.0000

Data Index: 1568084 (Python Code)

Max Activating Token Index: 375

Text #18

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.4993. Min Act: -0.0000

Data Index: 1399530 (Python Code)

Max Activating Token Index: 877

Text #19

Max Range: 3.6776. Min Range: -3.6776

Max Act: 1.4963. Min Act: -0.0000

Data Index: 1611740 (Python Code)

Max Activating Token Index: 40