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

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

Neuron 4589 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: 4.9691. Min Range: -4.9691

Max Act: 4.9691. Min Act: -0.0000

Data Index: 1109532 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.7638. Min Act: -0.0000

Data Index: 1604172 (Python Code)

Max Activating Token Index: 144

Text #2

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.9263. Min Act: -0.0000

Data Index: 460646 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.8787. Min Act: -0.0000

Data Index: 1369253 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.5859. Min Act: -0.0000

Data Index: 1612635 (Python Code)

Max Activating Token Index: 898

Text #5

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.5640. Min Act: -0.0000

Data Index: 857250 (C4 (Web Text))

Max Activating Token Index: 514

Text #6

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.4855. Min Act: -0.0000

Data Index: 1413487 (Python Code)

Max Activating Token Index: 90

Text #7

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.3071. Min Act: -0.0000

Data Index: 1436389 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.3981. Min Act: -0.0000

Data Index: 511159 (C4 (Web Text))

Max Activating Token Index: 762

Text #9

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.3021. Min Act: -0.0000

Data Index: 1596425 (Python Code)

Max Activating Token Index: 662

Text #10

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.2999. Min Act: -0.0000

Data Index: 1511635 (Python Code)

Max Activating Token Index: 447

Text #11

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.1293. Min Act: -0.0000

Data Index: 1392980 (Python Code)

Max Activating Token Index: 285

Text #12

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.0950. Min Act: -0.0000

Data Index: 1483680 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.0590. Min Act: -0.0000

Data Index: 704806 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.0351. Min Act: -0.0000

Data Index: 1587748 (Python Code)

Max Activating Token Index: 356

Text #15

Max Range: 4.9691. Min Range: -4.9691

Max Act: 3.1216. Min Act: -0.0000

Data Index: 1076102 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 4.9691. Min Range: -4.9691

Max Act: 2.9596. Min Act: -0.0000

Data Index: 1422253 (Python Code)

Max Activating Token Index: 495

Text #17

Max Range: 4.9691. Min Range: -4.9691

Max Act: 2.8149. Min Act: -0.0000

Data Index: 1570914 (Python Code)

Max Activating Token Index: 945

Text #18

Max Range: 4.9691. Min Range: -4.9691

Max Act: 2.9106. Min Act: -0.0000

Data Index: 1594988 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 4.9691. Min Range: -4.9691

Max Act: 2.8321. Min Act: -0.0000

Data Index: 1383626 (Python Code)

Max Activating Token Index: 176