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

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

Neuron 3832 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4626. Min Range: -3.4626

Max Act: 3.4626. Min Act: -0.0000

Data Index: 1449671 (Python Code)

Max Activating Token Index: 785

Text #1

Max Range: 3.4626. Min Range: -3.4626

Max Act: 3.0683. Min Act: 0.0000

Data Index: 1638111 (Python Code)

Max Activating Token Index: 926

Text #2

Max Range: 3.4626. Min Range: -3.4626

Max Act: 3.1166. Min Act: 0.0000

Data Index: 1593631 (Python Code)

Max Activating Token Index: 752

Text #3

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.6400. Min Act: 0.0000

Data Index: 1527006 (Python Code)

Max Activating Token Index: 688

Text #4

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.8825. Min Act: -0.0000

Data Index: 1468651 (Python Code)

Max Activating Token Index: 564

Text #5

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.6423. Min Act: -0.0000

Data Index: 1637505 (Python Code)

Max Activating Token Index: 715

Text #6

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5881. Min Act: 0.0000

Data Index: 1503834 (Python Code)

Max Activating Token Index: 818

Text #7

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.2189. Min Act: -0.0000

Data Index: 1431089 (Python Code)

Max Activating Token Index: 344

Text #8

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.4341. Min Act: 0.0000

Data Index: 1407456 (Python Code)

Max Activating Token Index: 911

Text #9

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.5164. Min Act: -0.0000

Data Index: 1540709 (Python Code)

Max Activating Token Index: 603

Text #10

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.6380. Min Act: 0.0000

Data Index: 1626549 (Python Code)

Max Activating Token Index: 526

Text #11

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.6526. Min Act: 0.0000

Data Index: 1636898 (Python Code)

Max Activating Token Index: 752

Text #12

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.3402. Min Act: -0.0000

Data Index: 1453883 (Python Code)

Max Activating Token Index: 312

Text #13

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.2027. Min Act: -0.0000

Data Index: 1401348 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.4062. Min Act: -0.0000

Data Index: 1407618 (Python Code)

Max Activating Token Index: 348

Text #15

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.1667. Min Act: -0.0000

Data Index: 1382415 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.4843. Min Act: -0.0000

Data Index: 1360851 (Python Code)

Max Activating Token Index: 648

Text #17

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.2451. Min Act: -0.0000

Data Index: 1654115 (Python Code)

Max Activating Token Index: 623

Text #18

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.1271. Min Act: -0.0000

Data Index: 1627838 (Python Code)

Max Activating Token Index: 703

Text #19

Max Range: 3.4626. Min Range: -3.4626

Max Act: 2.3492. Min Act: -0.0000

Data Index: 1606269 (Python Code)

Max Activating Token Index: 772