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

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

Neuron 2632 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.5053. Min Act: -0.0000

Data Index: 1601707 (Python Code)

Max Activating Token Index: 999

Text #1

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.1437. Min Act: -0.0000

Data Index: 1495788 (Python Code)

Max Activating Token Index: 52

Text #2

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.7102. Min Act: -0.0000

Data Index: 1379295 (Python Code)

Max Activating Token Index: 191

Text #3

Max Range: 4.5053. Min Range: -4.5053

Max Act: 4.0119. Min Act: -0.0000

Data Index: 1493937 (Python Code)

Max Activating Token Index: 134

Text #4

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.7423. Min Act: -0.0000

Data Index: 1426104 (Python Code)

Max Activating Token Index: 976

Text #5

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.5825. Min Act: -0.0000

Data Index: 1611241 (Python Code)

Max Activating Token Index: 755

Text #6

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.8528. Min Act: -0.0000

Data Index: 1592480 (Python Code)

Max Activating Token Index: 782

Text #7

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.5153. Min Act: -0.0000

Data Index: 1362261 (Python Code)

Max Activating Token Index: 719

Text #8

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.4079. Min Act: -0.0000

Data Index: 1513222 (Python Code)

Max Activating Token Index: 766

Text #9

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.0747. Min Act: -0.0000

Data Index: 1586027 (Python Code)

Max Activating Token Index: 887

Text #10

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.3589. Min Act: -0.0000

Data Index: 1440625 (Python Code)

Max Activating Token Index: 992

Text #11

Max Range: 4.5053. Min Range: -4.5053

Max Act: 2.8979. Min Act: -0.0000

Data Index: 1581960 (Python Code)

Max Activating Token Index: 159

Text #12

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.5077. Min Act: -0.0000

Data Index: 1400017 (Python Code)

Max Activating Token Index: 801

Text #13

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.3334. Min Act: -0.0000

Data Index: 1583313 (Python Code)

Max Activating Token Index: 309

Text #14

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.3190. Min Act: -0.0000

Data Index: 1562951 (Python Code)

Max Activating Token Index: 985

Text #15

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.1585. Min Act: -0.0000

Data Index: 1531105 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.4548. Min Act: -0.0000

Data Index: 1465638 (Python Code)

Max Activating Token Index: 564

Text #17

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.2542. Min Act: -0.0000

Data Index: 1535516 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.1106. Min Act: -0.0000

Data Index: 1548770 (Python Code)

Max Activating Token Index: 921

Text #19

Max Range: 4.5053. Min Range: -4.5053

Max Act: 3.2564. Min Act: -0.0000

Data Index: 1656830 (Python Code)

Max Activating Token Index: 175