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

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

Neuron 4944 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1604. Min Range: -4.1604

Max Act: 4.1604. Min Act: -0.0000

Data Index: 939884 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.9165. Min Act: -0.0000

Data Index: 1506155 (Python Code)

Max Activating Token Index: 592

Text #2

Max Range: 4.1604. Min Range: -4.1604

Max Act: 4.0074. Min Act: -0.0000

Data Index: 851520 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.5990. Min Act: -0.0000

Data Index: 1175830 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.5828. Min Act: -0.0000

Data Index: 972176 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.7495. Min Act: -0.0000

Data Index: 597949 (C4 (Web Text))

Max Activating Token Index: 781

Text #6

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.7142. Min Act: -0.0000

Data Index: 949726 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.6600. Min Act: -0.0000

Data Index: 18436 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.5933. Min Act: -0.0000

Data Index: 25951 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.4995. Min Act: -0.0000

Data Index: 867050 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.4763. Min Act: -0.0000

Data Index: 1524258 (Python Code)

Max Activating Token Index: 502

Text #11

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.3958. Min Act: -0.0000

Data Index: 1529801 (Python Code)

Max Activating Token Index: 930

Text #12

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.3955. Min Act: -0.0000

Data Index: 1456619 (Python Code)

Max Activating Token Index: 611

Text #13

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.3106. Min Act: -0.0000

Data Index: 413886 (C4 (Web Text))

Max Activating Token Index: 666

Text #14

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.3205. Min Act: -0.0000

Data Index: 977482 (C4 (Web Text))

Max Activating Token Index: 292

Text #15

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.3238. Min Act: -0.0000

Data Index: 1504927 (Python Code)

Max Activating Token Index: 430

Text #16

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.0946. Min Act: -0.0000

Data Index: 1038598 (C4 (Web Text))

Max Activating Token Index: 296

Text #17

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.3247. Min Act: -0.0000

Data Index: 1095747 (C4 (Web Text))

Max Activating Token Index: 962

Text #18

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.0257. Min Act: -0.0000

Data Index: 1383158 (Python Code)

Max Activating Token Index: 1002

Text #19

Max Range: 4.1604. Min Range: -4.1604

Max Act: 3.1538. Min Act: -0.0000

Data Index: 806677 (C4 (Web Text))

Max Activating Token Index: 531