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

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

Neuron 1892 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.8417. Min Act: -0.0001

Data Index: 1417720 (Python Code)

Max Activating Token Index: 153

Text #1

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7972. Min Act: -0.0001

Data Index: 1470328 (Python Code)

Max Activating Token Index: 854

Text #2

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7605. Min Act: -0.0001

Data Index: 1563532 (Python Code)

Max Activating Token Index: 351

Text #3

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6862. Min Act: -0.0001

Data Index: 1363698 (Python Code)

Max Activating Token Index: 715

Text #4

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1558690 (Python Code)

Max Activating Token Index: 868

Text #5

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6998. Min Act: -0.0001

Data Index: 1605190 (Python Code)

Max Activating Token Index: 373

Text #6

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7615. Min Act: -0.0001

Data Index: 1542137 (Python Code)

Max Activating Token Index: 264

Text #7

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7110. Min Act: -0.0001

Data Index: 1408105 (Python Code)

Max Activating Token Index: 373

Text #8

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6860. Min Act: -0.0001

Data Index: 1364834 (Python Code)

Max Activating Token Index: 638

Text #9

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.7103. Min Act: -0.0001

Data Index: 189489 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6584. Min Act: -0.0001

Data Index: 1556827 (Python Code)

Max Activating Token Index: 640

Text #11

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6986. Min Act: -0.0001

Data Index: 1368666 (Python Code)

Max Activating Token Index: 496

Text #12

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6773. Min Act: -0.0001

Data Index: 1398549 (Python Code)

Max Activating Token Index: 651

Text #13

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6513. Min Act: -0.0000

Data Index: 864831 (C4 (Web Text))

Max Activating Token Index: 494

Text #14

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6720. Min Act: -0.0001

Data Index: 1387741 (Python Code)

Max Activating Token Index: 580

Text #15

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6484. Min Act: -0.0001

Data Index: 1616104 (Python Code)

Max Activating Token Index: 193

Text #16

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6150. Min Act: -0.0001

Data Index: 1488491 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6703. Min Act: -0.0001

Data Index: 1564844 (Python Code)

Max Activating Token Index: 526

Text #18

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6688. Min Act: -0.0001

Data Index: 1597918 (Python Code)

Max Activating Token Index: 806

Text #19

Max Range: 0.8417. Min Range: -0.8417

Max Act: 0.6623. Min Act: -0.0001

Data Index: 935977 (C4 (Web Text))

Max Activating Token Index: 264