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

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

Neuron 3101 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: 0.7503. Min Range: -0.7503

Max Act: 0.7503. Min Act: -0.0001

Data Index: 325516 (C4 (Web Text))

Max Activating Token Index: 697

Text #1

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6441. Min Act: -0.0001

Data Index: 951396 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6501. Min Act: -0.0001

Data Index: 157531 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6614. Min Act: -0.0001

Data Index: 485284 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1348867 (C4 (Web Text))

Max Activating Token Index: 691

Text #5

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5721. Min Act: -0.0001

Data Index: 537300 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6354. Min Act: -0.0001

Data Index: 1006602 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5998. Min Act: -0.0001

Data Index: 777763 (C4 (Web Text))

Max Activating Token Index: 550

Text #8

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6001. Min Act: -0.0001

Data Index: 567897 (C4 (Web Text))

Max Activating Token Index: 45

Text #9

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6138. Min Act: -0.0001

Data Index: 1127365 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6062. Min Act: -0.0001

Data Index: 142255 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.6432. Min Act: -0.0001

Data Index: 615973 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5728. Min Act: -0.0001

Data Index: 1355513 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5702. Min Act: -0.0001

Data Index: 957698 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5789. Min Act: -0.0001

Data Index: 1020514 (C4 (Web Text))

Max Activating Token Index: 517

Text #15

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5542. Min Act: -0.0001

Data Index: 1223559 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5677. Min Act: -0.0001

Data Index: 957222 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5471. Min Act: -0.0001

Data Index: 1272791 (C4 (Web Text))

Max Activating Token Index: 48

Text #18

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5496. Min Act: -0.0001

Data Index: 1074612 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.7503. Min Range: -0.7503

Max Act: 0.5287. Min Act: -0.0001

Data Index: 923742 (C4 (Web Text))

Max Activating Token Index: 291