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

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

Neuron 5054 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9953. Min Act: -0.0002

Data Index: 1418449 (Python Code)

Max Activating Token Index: 368

Text #1

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9859. Min Act: -0.0002

Data Index: 1649522 (Python Code)

Max Activating Token Index: 25

Text #2

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9436. Min Act: -0.0002

Data Index: 1458952 (Python Code)

Max Activating Token Index: 144

Text #3

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9232. Min Act: -0.0002

Data Index: 1621376 (Python Code)

Max Activating Token Index: 428

Text #4

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8589. Min Act: -0.0002

Data Index: 1517446 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9311. Min Act: -0.0002

Data Index: 1463223 (Python Code)

Max Activating Token Index: 417

Text #6

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8795. Min Act: -0.0002

Data Index: 1528984 (Python Code)

Max Activating Token Index: 727

Text #7

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8679. Min Act: -0.0002

Data Index: 1390896 (Python Code)

Max Activating Token Index: 38

Text #8

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9281. Min Act: -0.0002

Data Index: 1518499 (Python Code)

Max Activating Token Index: 91

Text #9

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8709. Min Act: -0.0002

Data Index: 1372743 (Python Code)

Max Activating Token Index: 996

Text #10

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8607. Min Act: -0.0002

Data Index: 1426144 (Python Code)

Max Activating Token Index: 282

Text #11

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.7092. Min Act: -0.0002

Data Index: 1541768 (Python Code)

Max Activating Token Index: 281

Text #12

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9065. Min Act: -0.0002

Data Index: 1372972 (Python Code)

Max Activating Token Index: 522

Text #13

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.9319. Min Act: -0.0002

Data Index: 1509801 (Python Code)

Max Activating Token Index: 142

Text #14

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8763. Min Act: -0.0002

Data Index: 1513027 (Python Code)

Max Activating Token Index: 329

Text #15

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8528. Min Act: -0.0002

Data Index: 1500881 (Python Code)

Max Activating Token Index: 1019

Text #16

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8052. Min Act: -0.0002

Data Index: 1507835 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8574. Min Act: -0.0002

Data Index: 1433213 (Python Code)

Max Activating Token Index: 777

Text #18

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8513. Min Act: -0.0002

Data Index: 1526457 (Python Code)

Max Activating Token Index: 90

Text #19

Max Range: 0.9953. Min Range: -0.9953

Max Act: 0.8669. Min Act: -0.0002

Data Index: 1571559 (Python Code)

Max Activating Token Index: 495