Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 520 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.3160. Min Act: -0.0003

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.3336. Min Act: -0.0003

Data Index: 1643548 (Python Code)

Max Activating Token Index: 941

Text #2

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1770. Min Act: -0.0003

Data Index: 1421588 (Python Code)

Max Activating Token Index: 818

Text #3

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1830. Min Act: -0.0003

Data Index: 1409000 (Python Code)

Max Activating Token Index: 6

Text #4

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1838. Min Act: -0.0003

Data Index: 593933 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1466. Min Act: -0.0004

Data Index: 1119201 (C4 (Web Text))

Max Activating Token Index: 249

Text #6

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1534. Min Act: -0.0003

Data Index: 919090 (C4 (Web Text))

Max Activating Token Index: 952

Text #7

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1412. Min Act: -0.0003

Data Index: 1474538 (Python Code)

Max Activating Token Index: 939

Text #8

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1439. Min Act: -0.0003

Data Index: 1486112 (Python Code)

Max Activating Token Index: 413

Text #9

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1403. Min Act: -0.0003

Data Index: 1467808 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1219. Min Act: -0.0003

Data Index: 1421649 (Python Code)

Max Activating Token Index: 643

Text #11

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1244. Min Act: -0.0003

Data Index: 1497881 (Python Code)

Max Activating Token Index: 988

Text #12

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1107. Min Act: -0.0003

Data Index: 1392186 (Python Code)

Max Activating Token Index: 892

Text #13

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1081. Min Act: -0.0003

Data Index: 1575688 (Python Code)

Max Activating Token Index: 509

Text #14

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1003. Min Act: -0.0003

Data Index: 1212205 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1057. Min Act: -0.0003

Data Index: 1614526 (Python Code)

Max Activating Token Index: 720

Text #16

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1037. Min Act: -0.0003

Data Index: 1331118 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1038. Min Act: -0.0003

Data Index: 1400364 (Python Code)

Max Activating Token Index: 1011

Text #18

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.0998. Min Act: -0.0003

Data Index: 404889 (C4 (Web Text))

Max Activating Token Index: 929

Text #19

Max Range: 0.3336. Min Range: -0.3336

Max Act: 0.1046. Min Act: -0.0003

Data Index: 1596174 (Python Code)

Max Activating Token Index: 420