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

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

Neuron 32 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.7674. Min Act: -0.0002

Data Index: 1411717 (Python Code)

Max Activating Token Index: 969

Text #1

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.6722. Min Act: -0.0002

Data Index: 1460651 (Python Code)

Max Activating Token Index: 641

Text #2

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5933. Min Act: -0.0002

Data Index: 1628254 (Python Code)

Max Activating Token Index: 734

Text #3

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5801. Min Act: -0.0002

Data Index: 1484879 (Python Code)

Max Activating Token Index: 475

Text #4

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5145. Min Act: -0.0002

Data Index: 1476281 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5106. Min Act: -0.0002

Data Index: 1457643 (Python Code)

Max Activating Token Index: 154

Text #6

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5012. Min Act: -0.0002

Data Index: 1385141 (Python Code)

Max Activating Token Index: 53

Text #7

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5281. Min Act: -0.0002

Data Index: 1416863 (Python Code)

Max Activating Token Index: 39

Text #8

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4865. Min Act: -0.0002

Data Index: 1473150 (Python Code)

Max Activating Token Index: 99

Text #9

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5487. Min Act: -0.0002

Data Index: 1552566 (Python Code)

Max Activating Token Index: 99

Text #10

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5320. Min Act: -0.0002

Data Index: 1619829 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5277. Min Act: -0.0002

Data Index: 1388348 (Python Code)

Max Activating Token Index: 428

Text #12

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4970. Min Act: -0.0002

Data Index: 1470545 (Python Code)

Max Activating Token Index: 33

Text #13

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4563. Min Act: -0.0002

Data Index: 1613291 (Python Code)

Max Activating Token Index: 845

Text #14

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.5104. Min Act: -0.0002

Data Index: 1528484 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4811. Min Act: -0.0002

Data Index: 1404279 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4826. Min Act: -0.0002

Data Index: 1490023 (Python Code)

Max Activating Token Index: 104

Text #17

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4284. Min Act: -0.0002

Data Index: 1427066 (Python Code)

Max Activating Token Index: 810

Text #18

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4734. Min Act: -0.0002

Data Index: 1474744 (Python Code)

Max Activating Token Index: 37

Text #19

Max Range: 1.7674. Min Range: -1.7674

Max Act: 1.4466. Min Act: -0.0002

Data Index: 1519061 (Python Code)

Max Activating Token Index: 105