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

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

Neuron 3046 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7534. Min Act: -0.0001

Data Index: 121146 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1182202 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8227. Min Act: -0.0001

Data Index: 589588 (C4 (Web Text))

Max Activating Token Index: 363

Text #3

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7886. Min Act: -0.0001

Data Index: 1017719 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7551. Min Act: -0.0001

Data Index: 600178 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7574. Min Act: -0.0001

Data Index: 453390 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8006. Min Act: -0.0001

Data Index: 688590 (C4 (Web Text))

Max Activating Token Index: 669

Text #7

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7204. Min Act: -0.0001

Data Index: 1253785 (C4 (Web Text))

Max Activating Token Index: 691

Text #8

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7487. Min Act: -0.0001

Data Index: 396812 (C4 (Web Text))

Max Activating Token Index: 972

Text #9

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7138. Min Act: -0.0001

Data Index: 935155 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7491. Min Act: -0.0001

Data Index: 1156119 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7213. Min Act: -0.0001

Data Index: 849945 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6754. Min Act: -0.0001

Data Index: 1087664 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6768. Min Act: -0.0001

Data Index: 1073711 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.8089. Min Act: -0.0001

Data Index: 625617 (C4 (Web Text))

Max Activating Token Index: 172

Text #15

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7170. Min Act: -0.0001

Data Index: 340091 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6908. Min Act: -0.0001

Data Index: 24247 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.6939. Min Act: -0.0001

Data Index: 949977 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7570. Min Act: -0.0001

Data Index: 99221 (C4 (Web Text))

Max Activating Token Index: 554

Text #19

Max Range: 0.8227. Min Range: -0.8227

Max Act: 0.7069. Min Act: -0.0001

Data Index: 78708 (C4 (Web Text))

Max Activating Token Index: 317