Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3431 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.1593. Min Range: -1.1593

Max Act: 1.1593. Min Act: -0.0001

Data Index: 775767 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9449. Min Act: -0.0001

Data Index: 123683 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9531. Min Act: -0.0001

Data Index: 653837 (C4 (Web Text))

Max Activating Token Index: 940

Text #3

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9855. Min Act: -0.0001

Data Index: 445511 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9091. Min Act: -0.0001

Data Index: 959570 (C4 (Web Text))

Max Activating Token Index: 973

Text #5

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9314. Min Act: -0.0001

Data Index: 691990 (C4 (Web Text))

Max Activating Token Index: 648

Text #6

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9768. Min Act: -0.0001

Data Index: 317810 (C4 (Web Text))

Max Activating Token Index: 418

Text #7

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8614. Min Act: -0.0001

Data Index: 465933 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8776. Min Act: -0.0001

Data Index: 78508 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8489. Min Act: -0.0001

Data Index: 221660 (C4 (Web Text))

Max Activating Token Index: 263

Text #10

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8615. Min Act: -0.0001

Data Index: 291816 (C4 (Web Text))

Max Activating Token Index: 912

Text #11

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9424. Min Act: -0.0001

Data Index: 550524 (C4 (Web Text))

Max Activating Token Index: 608

Text #12

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8377. Min Act: -0.0001

Data Index: 349545 (C4 (Web Text))

Max Activating Token Index: 883

Text #13

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8584. Min Act: -0.0001

Data Index: 322479 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9012. Min Act: -0.0001

Data Index: 93801 (C4 (Web Text))

Max Activating Token Index: 903

Text #15

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.9158. Min Act: -0.0001

Data Index: 678363 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8556. Min Act: -0.0001

Data Index: 1126512 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8084. Min Act: -0.0001

Data Index: 1002631 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8144. Min Act: -0.0001

Data Index: 408316 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 1.1593. Min Range: -1.1593

Max Act: 0.8220. Min Act: -0.0001

Data Index: 1209389 (C4 (Web Text))

Max Activating Token Index: 265