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

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

Neuron 5233 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: 0.6510. Min Range: -0.6510

Max Act: 0.5772. Min Act: -0.0001

Data Index: 1541332 (Python Code)

Max Activating Token Index: 939

Text #1

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1459949 (Python Code)

Max Activating Token Index: 1007

Text #2

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1510320 (Python Code)

Max Activating Token Index: 909

Text #3

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5648. Min Act: -0.0000

Data Index: 1376264 (Python Code)

Max Activating Token Index: 1015

Text #4

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5780. Min Act: -0.0001

Data Index: 1528340 (Python Code)

Max Activating Token Index: 833

Text #5

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.4969. Min Act: -0.0000

Data Index: 1546397 (Python Code)

Max Activating Token Index: 877

Text #6

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1371929 (Python Code)

Max Activating Token Index: 945

Text #7

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1400577 (Python Code)

Max Activating Token Index: 683

Text #8

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5265. Min Act: -0.0001

Data Index: 1633235 (Python Code)

Max Activating Token Index: 883

Text #9

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1561313 (Python Code)

Max Activating Token Index: 922

Text #10

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5571. Min Act: -0.0000

Data Index: 1486396 (Python Code)

Max Activating Token Index: 894

Text #11

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5574. Min Act: -0.0000

Data Index: 1485393 (Python Code)

Max Activating Token Index: 937

Text #12

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5038. Min Act: -0.0001

Data Index: 1376589 (Python Code)

Max Activating Token Index: 975

Text #13

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5332. Min Act: -0.0001

Data Index: 1605673 (Python Code)

Max Activating Token Index: 933

Text #14

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5377. Min Act: -0.0001

Data Index: 1516195 (Python Code)

Max Activating Token Index: 1020

Text #15

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5656. Min Act: -0.0000

Data Index: 1629745 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5286. Min Act: -0.0000

Data Index: 1508072 (Python Code)

Max Activating Token Index: 701

Text #17

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.4804. Min Act: -0.0001

Data Index: 1635926 (Python Code)

Max Activating Token Index: 603

Text #18

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1335595 (C4 (Web Text))

Max Activating Token Index: 636

Text #19

Max Range: 0.6510. Min Range: -0.6510

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1642946 (Python Code)

Max Activating Token Index: 942