Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1159 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0593. Min Act: -0.0006

Data Index: 1182075 (C4 (Web Text))

Max Activating Token Index: 962

Text #1

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0559. Min Act: -0.0006

Data Index: 811792 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0533. Min Act: -0.0006

Data Index: 91191 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0452. Min Act: -0.0006

Data Index: 1357625 (C4 (Web Text))

Max Activating Token Index: 908

Text #4

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0437. Min Act: -0.0006

Data Index: 817130 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0450. Min Act: -0.0006

Data Index: 405660 (C4 (Web Text))

Max Activating Token Index: 556

Text #6

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0403. Min Act: -0.0006

Data Index: 1124144 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0416. Min Act: -0.0006

Data Index: 1373729 (Python Code)

Max Activating Token Index: 1004

Text #8

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0447. Min Act: -0.0006

Data Index: 1157869 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0427. Min Act: -0.0006

Data Index: 504002 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0395. Min Act: -0.0006

Data Index: 1466573 (Python Code)

Max Activating Token Index: 688

Text #11

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0420. Min Act: -0.0006

Data Index: 1359373 (C4 (Web Text))

Max Activating Token Index: 1016

Text #12

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0416. Min Act: -0.0006

Data Index: 759495 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0424. Min Act: -0.0006

Data Index: 1042815 (C4 (Web Text))

Max Activating Token Index: 331

Text #14

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0438. Min Act: -0.0006

Data Index: 1500851 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0437. Min Act: -0.0006

Data Index: 345181 (C4 (Web Text))

Max Activating Token Index: 303

Text #16

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0389. Min Act: -0.0006

Data Index: 707585 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0400. Min Act: -0.0006

Data Index: 1161912 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0400. Min Act: -0.0006

Data Index: 40577 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.0593. Min Range: -0.0593

Max Act: 0.0397. Min Act: -0.0006

Data Index: 1447401 (Python Code)

Max Activating Token Index: 957