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

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

Neuron 1309 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: 0.6007. Min Range: -0.6007

Max Act: 0.6007. Min Act: -0.0002

Data Index: 1413405 (Python Code)

Max Activating Token Index: 582

Text #1

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5726. Min Act: -0.0002

Data Index: 1603650 (Python Code)

Max Activating Token Index: 151

Text #2

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5473. Min Act: -0.0002

Data Index: 173459 (C4 (Web Text))

Max Activating Token Index: 48

Text #3

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5467. Min Act: -0.0002

Data Index: 1530944 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5397. Min Act: -0.0002

Data Index: 906798 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5367. Min Act: -0.0002

Data Index: 1558258 (Python Code)

Max Activating Token Index: 109

Text #6

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5151. Min Act: -0.0002

Data Index: 1530095 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5096. Min Act: -0.0002

Data Index: 1556188 (Python Code)

Max Activating Token Index: 823

Text #8

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5078. Min Act: -0.0002

Data Index: 1444856 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5054. Min Act: -0.0002

Data Index: 643279 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4980. Min Act: -0.0002

Data Index: 1501093 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5043. Min Act: -0.0002

Data Index: 444630 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.5052. Min Act: -0.0002

Data Index: 498547 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4863. Min Act: -0.0002

Data Index: 1399477 (Python Code)

Max Activating Token Index: 940

Text #14

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4974. Min Act: -0.0002

Data Index: 1437743 (Python Code)

Max Activating Token Index: 907

Text #15

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4896. Min Act: -0.0002

Data Index: 395034 (C4 (Web Text))

Max Activating Token Index: 222

Text #16

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4828. Min Act: -0.0002

Data Index: 1541417 (Python Code)

Max Activating Token Index: 582

Text #17

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4838. Min Act: -0.0002

Data Index: 1397867 (Python Code)

Max Activating Token Index: 538

Text #18

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4744. Min Act: -0.0002

Data Index: 1473937 (Python Code)

Max Activating Token Index: 994

Text #19

Max Range: 0.6007. Min Range: -0.6007

Max Act: 0.4762. Min Act: -0.0002

Data Index: 200791 (C4 (Web Text))

Max Activating Token Index: 676