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

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

Neuron 114 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1899. Min Act: -0.0001

Data Index: 330117 (C4 (Web Text))

Max Activating Token Index: 521

Text #1

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1707. Min Act: -0.0001

Data Index: 854931 (C4 (Web Text))

Max Activating Token Index: 685

Text #2

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1637. Min Act: -0.0001

Data Index: 532745 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1536. Min Act: -0.0001

Data Index: 49701 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1069743 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1371. Min Act: -0.0001

Data Index: 844333 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1134997 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1663. Min Act: -0.0001

Data Index: 736709 (C4 (Web Text))

Max Activating Token Index: 228

Text #8

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1523. Min Act: -0.0001

Data Index: 485942 (C4 (Web Text))

Max Activating Token Index: 229

Text #9

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1410. Min Act: -0.0001

Data Index: 27596 (C4 (Web Text))

Max Activating Token Index: 706

Text #10

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1356. Min Act: -0.0001

Data Index: 655514 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1322. Min Act: -0.0001

Data Index: 124310 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.0980. Min Act: -0.0001

Data Index: 226501 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.1032. Min Act: -0.0001

Data Index: 381467 (C4 (Web Text))

Max Activating Token Index: 641

Text #14

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.0952. Min Act: -0.0001

Data Index: 568598 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.0918. Min Act: -0.0001

Data Index: 917576 (C4 (Web Text))

Max Activating Token Index: 51

Text #16

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1054875 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1048598 (C4 (Web Text))

Max Activating Token Index: 936

Text #18

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1346031 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.1899. Min Range: -0.1899

Max Act: 0.0734. Min Act: -0.0001

Data Index: 370181 (C4 (Web Text))

Max Activating Token Index: 377