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

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

Neuron 1378 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.9417. Min Act: -0.0000

Data Index: 1622014 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.9302. Min Act: -0.0000

Data Index: 1408041 (Python Code)

Max Activating Token Index: 798

Text #2

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.6773. Min Act: -0.0000

Data Index: 1480878 (Python Code)

Max Activating Token Index: 389

Text #3

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.6680. Min Act: -0.0000

Data Index: 1410024 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.7464. Min Act: -0.0000

Data Index: 1619596 (Python Code)

Max Activating Token Index: 728

Text #5

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.5791. Min Act: -0.0000

Data Index: 1560953 (Python Code)

Max Activating Token Index: 880

Text #6

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.5649. Min Act: -0.0000

Data Index: 1410419 (Python Code)

Max Activating Token Index: 522

Text #7

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.6718. Min Act: -0.0000

Data Index: 1415873 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.5128. Min Act: -0.0000

Data Index: 1574503 (Python Code)

Max Activating Token Index: 1010

Text #9

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.5025. Min Act: -0.0000

Data Index: 1463350 (Python Code)

Max Activating Token Index: 785

Text #10

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.6087. Min Act: -0.0000

Data Index: 1515677 (Python Code)

Max Activating Token Index: 858

Text #11

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.5530. Min Act: -0.0000

Data Index: 1618813 (Python Code)

Max Activating Token Index: 340

Text #12

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.6550. Min Act: -0.0000

Data Index: 1624891 (Python Code)

Max Activating Token Index: 864

Text #13

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.3442. Min Act: -0.0000

Data Index: 1648065 (Python Code)

Max Activating Token Index: 128

Text #14

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.3341. Min Act: -0.0000

Data Index: 1573705 (Python Code)

Max Activating Token Index: 396

Text #15

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.4525. Min Act: -0.0000

Data Index: 1451871 (Python Code)

Max Activating Token Index: 542

Text #16

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.2998. Min Act: -0.0000

Data Index: 1485777 (Python Code)

Max Activating Token Index: 966

Text #17

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.4353. Min Act: -0.0000

Data Index: 1586348 (Python Code)

Max Activating Token Index: 984

Text #18

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.4309. Min Act: -0.0000

Data Index: 1651626 (Python Code)

Max Activating Token Index: 265

Text #19

Max Range: 2.9417. Min Range: -2.9417

Max Act: 2.5209. Min Act: -0.0000

Data Index: 1468921 (Python Code)

Max Activating Token Index: 28