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

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

Neuron 1531 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8642. Min Act: -0.0001

Data Index: 1037671 (C4 (Web Text))

Max Activating Token Index: 875

Text #1

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7894. Min Act: -0.0001

Data Index: 1148001 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8358. Min Act: -0.0001

Data Index: 1214539 (C4 (Web Text))

Max Activating Token Index: 894

Text #3

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1205490 (C4 (Web Text))

Max Activating Token Index: 949

Text #4

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7928. Min Act: -0.0001

Data Index: 25939 (C4 (Web Text))

Max Activating Token Index: 129

Text #5

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7336. Min Act: -0.0001

Data Index: 553504 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.8088. Min Act: -0.0000

Data Index: 208459 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7776. Min Act: -0.0000

Data Index: 456867 (C4 (Web Text))

Max Activating Token Index: 681

Text #8

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7463. Min Act: -0.0000

Data Index: 586679 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7749. Min Act: -0.0000

Data Index: 1266438 (C4 (Web Text))

Max Activating Token Index: 377

Text #10

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7900. Min Act: -0.0000

Data Index: 851977 (C4 (Web Text))

Max Activating Token Index: 57

Text #11

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7029. Min Act: -0.0001

Data Index: 103387 (C4 (Web Text))

Max Activating Token Index: 380

Text #12

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7441. Min Act: -0.0001

Data Index: 1182945 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7432. Min Act: -0.0000

Data Index: 448826 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7423. Min Act: -0.0000

Data Index: 848931 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7370. Min Act: -0.0000

Data Index: 510928 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7387. Min Act: -0.0000

Data Index: 1043116 (C4 (Web Text))

Max Activating Token Index: 1020

Text #17

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7356. Min Act: -0.0000

Data Index: 577671 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.7261. Min Act: -0.0001

Data Index: 384355 (C4 (Web Text))

Max Activating Token Index: 642

Text #19

Max Range: 0.8642. Min Range: -0.8642

Max Act: 0.6838. Min Act: -0.0000

Data Index: 672474 (C4 (Web Text))

Max Activating Token Index: 792