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

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

Neuron 2152 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.2381. Min Act: -0.0000

Data Index: 280905 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1336737 (C4 (Web Text))

Max Activating Token Index: 327

Text #2

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.0994. Min Act: -0.0000

Data Index: 889735 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.0577. Min Act: -0.0000

Data Index: 1213621 (C4 (Web Text))

Max Activating Token Index: 886

Text #4

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.1142. Min Act: -0.0000

Data Index: 1133166 (C4 (Web Text))

Max Activating Token Index: 1016

Text #5

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.0105. Min Act: -0.0000

Data Index: 859259 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9874. Min Act: -0.0000

Data Index: 114552 (C4 (Web Text))

Max Activating Token Index: 803

Text #7

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.0582. Min Act: -0.0000

Data Index: 553224 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.2381. Min Range: -1.2381

Max Act: 1.0530. Min Act: -0.0000

Data Index: 548169 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9485. Min Act: -0.0000

Data Index: 144487 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9115. Min Act: -0.0000

Data Index: 341088 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9053. Min Act: -0.0000

Data Index: 1094952 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9953. Min Act: -0.0000

Data Index: 674765 (C4 (Web Text))

Max Activating Token Index: 335

Text #13

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8463. Min Act: -0.0000

Data Index: 316925 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8914. Min Act: -0.0000

Data Index: 54587 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8320. Min Act: -0.0000

Data Index: 656718 (C4 (Web Text))

Max Activating Token Index: 316

Text #16

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.9019. Min Act: -0.0000

Data Index: 58043 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8504. Min Act: -0.0000

Data Index: 418164 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8001. Min Act: -0.0000

Data Index: 721849 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 1.2381. Min Range: -1.2381

Max Act: 0.8784. Min Act: -0.0000

Data Index: 468434 (C4 (Web Text))

Max Activating Token Index: 515