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

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

Neuron 1189 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.6422. Min Act: -0.0000

Data Index: 1489443 (Python Code)

Max Activating Token Index: 913

Text #1

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.5958. Min Act: -0.0000

Data Index: 1376028 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4911. Min Act: -0.0000

Data Index: 1366764 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.5473. Min Act: -0.0000

Data Index: 1477345 (Python Code)

Max Activating Token Index: 927

Text #4

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.6118. Min Act: -0.0000

Data Index: 1481674 (Python Code)

Max Activating Token Index: 771

Text #5

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1605054 (Python Code)

Max Activating Token Index: 710

Text #6

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1367545 (Python Code)

Max Activating Token Index: 1020

Text #7

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4283. Min Act: -0.0000

Data Index: 1444970 (Python Code)

Max Activating Token Index: 783

Text #8

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4775. Min Act: -0.0000

Data Index: 1646135 (Python Code)

Max Activating Token Index: 908

Text #9

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.3817. Min Act: -0.0000

Data Index: 1483374 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.3848. Min Act: -0.0000

Data Index: 1655404 (Python Code)

Max Activating Token Index: 847

Text #11

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4627. Min Act: -0.0000

Data Index: 1506226 (Python Code)

Max Activating Token Index: 573

Text #12

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4435. Min Act: -0.0000

Data Index: 1642910 (Python Code)

Max Activating Token Index: 583

Text #13

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4768. Min Act: 0.0000

Data Index: 1527644 (Python Code)

Max Activating Token Index: 820

Text #14

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.3082. Min Act: 0.0000

Data Index: 1626253 (Python Code)

Max Activating Token Index: 884

Text #15

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1428741 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.4058. Min Act: -0.0000

Data Index: 1361863 (Python Code)

Max Activating Token Index: 1019

Text #17

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1403796 (Python Code)

Max Activating Token Index: 579

Text #18

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.3655. Min Act: -0.0000

Data Index: 1626404 (Python Code)

Max Activating Token Index: 340

Text #19

Max Range: 1.6422. Min Range: -1.6422

Max Act: 1.2633. Min Act: -0.0000

Data Index: 1397498 (Python Code)

Max Activating Token Index: 799