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

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

Neuron 2050 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0820. Min Range: -1.0820

Max Act: 1.0742. Min Act: -0.0001

Data Index: 172345 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 1.0820. Min Range: -1.0820

Max Act: 1.0820. Min Act: -0.0001

Data Index: 209058 (C4 (Web Text))

Max Activating Token Index: 972

Text #2

Max Range: 1.0820. Min Range: -1.0820

Max Act: 1.0284. Min Act: -0.0001

Data Index: 732610 (C4 (Web Text))

Max Activating Token Index: 299

Text #3

Max Range: 1.0820. Min Range: -1.0820

Max Act: 1.0171. Min Act: -0.0001

Data Index: 353938 (C4 (Web Text))

Max Activating Token Index: 591

Text #4

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.9527. Min Act: -0.0001

Data Index: 332801 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8455. Min Act: -0.0001

Data Index: 59572 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8700. Min Act: -0.0001

Data Index: 1221699 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8950. Min Act: -0.0001

Data Index: 768935 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7842. Min Act: -0.0001

Data Index: 144252 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8852. Min Act: -0.0001

Data Index: 554221 (C4 (Web Text))

Max Activating Token Index: 165

Text #10

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7947. Min Act: -0.0001

Data Index: 1346016 (C4 (Web Text))

Max Activating Token Index: 435

Text #11

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8177. Min Act: -0.0001

Data Index: 1051428 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8410. Min Act: -0.0001

Data Index: 584961 (C4 (Web Text))

Max Activating Token Index: 452

Text #13

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8199. Min Act: -0.0001

Data Index: 561888 (C4 (Web Text))

Max Activating Token Index: 227

Text #14

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8089. Min Act: -0.0001

Data Index: 469066 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8573. Min Act: -0.0001

Data Index: 698150 (C4 (Web Text))

Max Activating Token Index: 206

Text #16

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8462. Min Act: -0.0001

Data Index: 1062930 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7979. Min Act: -0.0001

Data Index: 726671 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.7693. Min Act: -0.0001

Data Index: 150779 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 1.0820. Min Range: -1.0820

Max Act: 0.8110. Min Act: -0.0001

Data Index: 359176 (C4 (Web Text))

Max Activating Token Index: 504