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

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

Neuron 2988 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: 2.9018. Min Range: -2.9018

Max Act: 2.9018. Min Act: -0.0000

Data Index: 1453853 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 2.9018. Min Range: -2.9018

Max Act: 2.2986. Min Act: 0.0000

Data Index: 1381034 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 2.9018. Min Range: -2.9018

Max Act: 2.4513. Min Act: -0.0000

Data Index: 1429670 (Python Code)

Max Activating Token Index: 11

Text #3

Max Range: 2.9018. Min Range: -2.9018

Max Act: 2.0723. Min Act: 0.0000

Data Index: 1508899 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.7424. Min Act: 0.0000

Data Index: 1446822 (Python Code)

Max Activating Token Index: 7

Text #5

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.8018. Min Act: 0.0000

Data Index: 1620909 (Python Code)

Max Activating Token Index: 16

Text #6

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.7554. Min Act: 0.0000

Data Index: 1559073 (Python Code)

Max Activating Token Index: 46

Text #7

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.7082. Min Act: 0.0000

Data Index: 1464604 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.6225. Min Act: 0.0000

Data Index: 1558575 (Python Code)

Max Activating Token Index: 10

Text #9

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.6983. Min Act: 0.0000

Data Index: 1546258 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1470622 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.4911. Min Act: 0.0000

Data Index: 1492196 (Python Code)

Max Activating Token Index: 21

Text #12

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.5462. Min Act: 0.0000

Data Index: 1649850 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.4516. Min Act: -0.0000

Data Index: 1393562 (Python Code)

Max Activating Token Index: 243

Text #14

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.6136. Min Act: -0.0000

Data Index: 1587056 (Python Code)

Max Activating Token Index: 447

Text #15

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.4139. Min Act: -0.0000

Data Index: 1597814 (Python Code)

Max Activating Token Index: 907

Text #16

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.3943. Min Act: -0.0000

Data Index: 1416620 (Python Code)

Max Activating Token Index: 402

Text #17

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.4658. Min Act: -0.0000

Data Index: 1412739 (Python Code)

Max Activating Token Index: 464

Text #18

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.3664. Min Act: -0.0000

Data Index: 1562679 (Python Code)

Max Activating Token Index: 203

Text #19

Max Range: 2.9018. Min Range: -2.9018

Max Act: 1.4154. Min Act: -0.0000

Data Index: 1515682 (Python Code)

Max Activating Token Index: 14