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

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

Neuron 725 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: 2.1856. Min Range: -2.1856

Max Act: 2.1856. Min Act: -0.0000

Data Index: 742026 (C4 (Web Text))

Max Activating Token Index: 583

Text #1

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.9239. Min Act: -0.0000

Data Index: 1254323 (C4 (Web Text))

Max Activating Token Index: 950

Text #2

Max Range: 2.1856. Min Range: -2.1856

Max Act: 2.0014. Min Act: -0.0000

Data Index: 1323664 (C4 (Web Text))

Max Activating Token Index: 690

Text #3

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.7517. Min Act: -0.0000

Data Index: 1198865 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.6235. Min Act: -0.0000

Data Index: 638027 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.7216. Min Act: -0.0000

Data Index: 1143528 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.8707. Min Act: -0.0000

Data Index: 640207 (C4 (Web Text))

Max Activating Token Index: 247

Text #7

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.6129. Min Act: -0.0000

Data Index: 585372 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.5021. Min Act: -0.0000

Data Index: 467114 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.5638. Min Act: -0.0000

Data Index: 254242 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.4684. Min Act: -0.0000

Data Index: 250108 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.4626. Min Act: -0.0000

Data Index: 385191 (C4 (Web Text))

Max Activating Token Index: 276

Text #12

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.3815. Min Act: -0.0000

Data Index: 819325 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.5240. Min Act: -0.0000

Data Index: 624452 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.3429. Min Act: -0.0000

Data Index: 4043 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.4956. Min Act: -0.0000

Data Index: 785852 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.3889. Min Act: -0.0000

Data Index: 664820 (C4 (Web Text))

Max Activating Token Index: 637

Text #17

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.3888. Min Act: -0.0000

Data Index: 421450 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.2983. Min Act: -0.0000

Data Index: 468644 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 2.1856. Min Range: -2.1856

Max Act: 1.3639. Min Act: -0.0000

Data Index: 97324 (C4 (Web Text))

Max Activating Token Index: 965