Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1944 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.4063. Min Act: -0.0000

Data Index: 1019699 (C4 (Web Text))

Max Activating Token Index: 704

Text #1

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.3686. Min Act: -0.0000

Data Index: 997481 (C4 (Web Text))

Max Activating Token Index: 434

Text #2

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.3075. Min Act: -0.0000

Data Index: 730110 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.2958. Min Act: -0.0000

Data Index: 140397 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.3764. Min Act: -0.0000

Data Index: 800265 (C4 (Web Text))

Max Activating Token Index: 768

Text #5

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.1253. Min Act: -0.0000

Data Index: 352833 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.2138. Min Act: -0.0000

Data Index: 445549 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.2093. Min Act: -0.0000

Data Index: 123810 (C4 (Web Text))

Max Activating Token Index: 970

Text #8

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.1756. Min Act: -0.0000

Data Index: 1061419 (C4 (Web Text))

Max Activating Token Index: 840

Text #9

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0408. Min Act: -0.0000

Data Index: 887626 (C4 (Web Text))

Max Activating Token Index: 929

Text #10

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.2530. Min Act: -0.0000

Data Index: 354808 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0269. Min Act: -0.0000

Data Index: 59404 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0617. Min Act: -0.0000

Data Index: 632894 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0669. Min Act: -0.0000

Data Index: 883359 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.1792. Min Act: -0.0000

Data Index: 831535 (C4 (Web Text))

Max Activating Token Index: 345

Text #15

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0538. Min Act: -0.0000

Data Index: 43304 (C4 (Web Text))

Max Activating Token Index: 140

Text #16

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0583. Min Act: -0.0000

Data Index: 987248 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0311. Min Act: -0.0000

Data Index: 111037 (C4 (Web Text))

Max Activating Token Index: 935

Text #18

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0294. Min Act: -0.0000

Data Index: 922390 (C4 (Web Text))

Max Activating Token Index: 970

Text #19

Max Range: 2.4063. Min Range: -2.4063

Max Act: 2.0103. Min Act: -0.0000

Data Index: 837111 (C4 (Web Text))

Max Activating Token Index: 927