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

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

Neuron 2105 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.8886. Min Act: -0.0000

Data Index: 176589 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.7991. Min Act: -0.0000

Data Index: 490793 (C4 (Web Text))

Max Activating Token Index: 664

Text #2

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.7296. Min Act: -0.0000

Data Index: 948825 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5650. Min Act: -0.0000

Data Index: 1240240 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.6133. Min Act: -0.0000

Data Index: 874147 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5720. Min Act: -0.0000

Data Index: 756736 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.6104. Min Act: -0.0000

Data Index: 1315479 (C4 (Web Text))

Max Activating Token Index: 597

Text #7

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5998. Min Act: -0.0000

Data Index: 170878 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5851. Min Act: -0.0000

Data Index: 927847 (C4 (Web Text))

Max Activating Token Index: 901

Text #9

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.4879. Min Act: -0.0000

Data Index: 868959 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5032. Min Act: -0.0000

Data Index: 1203491 (C4 (Web Text))

Max Activating Token Index: 972

Text #11

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.7095. Min Act: -0.0000

Data Index: 496553 (C4 (Web Text))

Max Activating Token Index: 134

Text #12

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.4630. Min Act: -0.0000

Data Index: 1502300 (Python Code)

Max Activating Token Index: 416

Text #13

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5083. Min Act: -0.0000

Data Index: 61805 (C4 (Web Text))

Max Activating Token Index: 263

Text #14

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5138. Min Act: -0.0000

Data Index: 495345 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1268100 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5342. Min Act: -0.0000

Data Index: 1165758 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.4802. Min Act: -0.0000

Data Index: 898137 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5135. Min Act: -0.0000

Data Index: 469079 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 1.8886. Min Range: -1.8886

Max Act: 1.5165. Min Act: -0.0000

Data Index: 738470 (C4 (Web Text))

Max Activating Token Index: 102