Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 275 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.7032. Min Range: -2.7032

Max Act: 2.7032. Min Act: -0.0000

Data Index: 664872 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 2.7032. Min Range: -2.7032

Max Act: 2.3990. Min Act: -0.0000

Data Index: 842034 (C4 (Web Text))

Max Activating Token Index: 728

Text #2

Max Range: 2.7032. Min Range: -2.7032

Max Act: 2.3961. Min Act: -0.0000

Data Index: 1114614 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 2.7032. Min Range: -2.7032

Max Act: 2.2454. Min Act: -0.0001

Data Index: 658917 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 2.7032. Min Range: -2.7032

Max Act: 2.0995. Min Act: -0.0000

Data Index: 216233 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.9443. Min Act: -0.0001

Data Index: 888545 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 2.7032. Min Range: -2.7032

Max Act: 2.0958. Min Act: -0.0000

Data Index: 296606 (C4 (Web Text))

Max Activating Token Index: 913

Text #7

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.6457. Min Act: -0.0001

Data Index: 250816 (C4 (Web Text))

Max Activating Token Index: 413

Text #8

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.8882. Min Act: -0.0001

Data Index: 1174761 (C4 (Web Text))

Max Activating Token Index: 202

Text #9

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.9121. Min Act: -0.0001

Data Index: 1116424 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.7024. Min Act: -0.0001

Data Index: 815521 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.6328. Min Act: -0.0000

Data Index: 1050954 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.6403. Min Act: -0.0000

Data Index: 628519 (C4 (Web Text))

Max Activating Token Index: 583

Text #13

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.4950. Min Act: -0.0001

Data Index: 463142 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.5376. Min Act: -0.0000

Data Index: 1109378 (C4 (Web Text))

Max Activating Token Index: 930

Text #15

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.4339. Min Act: -0.0001

Data Index: 412201 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.4794. Min Act: -0.0000

Data Index: 496984 (C4 (Web Text))

Max Activating Token Index: 980

Text #17

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.4424. Min Act: -0.0000

Data Index: 462181 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.1964. Min Act: -0.0001

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 2.7032. Min Range: -2.7032

Max Act: 1.2921. Min Act: -0.0000

Data Index: 420192 (C4 (Web Text))

Max Activating Token Index: 253