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

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

Neuron 3390 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: 3.2961. Min Range: -3.2961

Max Act: 3.2961. Min Act: -0.0000

Data Index: 1440690 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 3.2961. Min Range: -3.2961

Max Act: 3.1019. Min Act: -0.0000

Data Index: 1491746 (Python Code)

Max Activating Token Index: 444

Text #2

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.9677. Min Act: -0.0000

Data Index: 1635027 (Python Code)

Max Activating Token Index: 406

Text #3

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.9114. Min Act: -0.0000

Data Index: 1504089 (Python Code)

Max Activating Token Index: 426

Text #4

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.8744. Min Act: -0.0001

Data Index: 1496649 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.8659. Min Act: -0.0000

Data Index: 1647983 (Python Code)

Max Activating Token Index: 719

Text #6

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.8483. Min Act: -0.0000

Data Index: 1619479 (Python Code)

Max Activating Token Index: 1021

Text #7

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.7503. Min Act: -0.0000

Data Index: 1504323 (Python Code)

Max Activating Token Index: 707

Text #8

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.5734. Min Act: -0.0000

Data Index: 1528746 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.7825. Min Act: -0.0000

Data Index: 1495522 (Python Code)

Max Activating Token Index: 554

Text #10

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.6478. Min Act: -0.0001

Data Index: 1413884 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.6138. Min Act: -0.0000

Data Index: 1630642 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.5452. Min Act: -0.0001

Data Index: 1595734 (Python Code)

Max Activating Token Index: 903

Text #13

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.4978. Min Act: -0.0000

Data Index: 1419920 (Python Code)

Max Activating Token Index: 973

Text #14

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.4841. Min Act: -0.0000

Data Index: 1613646 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.4332. Min Act: -0.0001

Data Index: 1468188 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.2459. Min Act: -0.0000

Data Index: 1577842 (Python Code)

Max Activating Token Index: 473

Text #17

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.3591. Min Act: -0.0000

Data Index: 1392240 (Python Code)

Max Activating Token Index: 501

Text #18

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.3614. Min Act: -0.0000

Data Index: 509497 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 3.2961. Min Range: -3.2961

Max Act: 2.2159. Min Act: -0.0000

Data Index: 1388969 (Python Code)

Max Activating Token Index: 925