Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4804 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0986. Min Range: -4.0986

Max Act: 4.0986. Min Act: -0.0000

Data Index: 1443284 (Python Code)

Max Activating Token Index: 29

Text #1

Max Range: 4.0986. Min Range: -4.0986

Max Act: 3.7398. Min Act: -0.0000

Data Index: 1390045 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 4.0986. Min Range: -4.0986

Max Act: 3.4527. Min Act: -0.0000

Data Index: 1651269 (Python Code)

Max Activating Token Index: 23

Text #3

Max Range: 4.0986. Min Range: -4.0986

Max Act: 3.2545. Min Act: -0.0000

Data Index: 1420587 (Python Code)

Max Activating Token Index: 25

Text #4

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.8075. Min Act: -0.0000

Data Index: 1600651 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 4.0986. Min Range: -4.0986

Max Act: 3.1973. Min Act: -0.0000

Data Index: 1422838 (Python Code)

Max Activating Token Index: 39

Text #6

Max Range: 4.0986. Min Range: -4.0986

Max Act: 3.1596. Min Act: -0.0000

Data Index: 1590711 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.9339. Min Act: 0.0000

Data Index: 1605297 (Python Code)

Max Activating Token Index: 45

Text #8

Max Range: 4.0986. Min Range: -4.0986

Max Act: 3.0731. Min Act: -0.0000

Data Index: 1474325 (Python Code)

Max Activating Token Index: 33

Text #9

Max Range: 4.0986. Min Range: -4.0986

Max Act: 3.0013. Min Act: -0.0000

Data Index: 1548696 (Python Code)

Max Activating Token Index: 21

Text #10

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.9395. Min Act: -0.0000

Data Index: 1565321 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.8990. Min Act: -0.0000

Data Index: 1594329 (Python Code)

Max Activating Token Index: 82

Text #12

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.8456. Min Act: -0.0000

Data Index: 1485156 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.8456. Min Act: -0.0000

Data Index: 1466545 (Python Code)

Max Activating Token Index: 6

Text #14

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.7036. Min Act: -0.0000

Data Index: 1414725 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.6704. Min Act: -0.0000

Data Index: 1535859 (Python Code)

Max Activating Token Index: 14

Text #16

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.8052. Min Act: -0.0000

Data Index: 1600803 (Python Code)

Max Activating Token Index: 73

Text #17

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.6325. Min Act: -0.0000

Data Index: 1468119 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.6626. Min Act: -0.0000

Data Index: 1604417 (Python Code)

Max Activating Token Index: 22

Text #19

Max Range: 4.0986. Min Range: -4.0986

Max Act: 2.6432. Min Act: -0.0000

Data Index: 1627098 (Python Code)

Max Activating Token Index: 43