Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1977 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1096. Min Act: -0.0001

Data Index: 1594983 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1389232 (Python Code)

Max Activating Token Index: 958

Text #2

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1406617 (Python Code)

Max Activating Token Index: 712

Text #3

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1500611 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0977. Min Act: -0.0002

Data Index: 1482345 (Python Code)

Max Activating Token Index: 966

Text #5

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1623060 (Python Code)

Max Activating Token Index: 304

Text #6

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0965. Min Act: -0.0002

Data Index: 1386370 (Python Code)

Max Activating Token Index: 942

Text #7

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1560204 (Python Code)

Max Activating Token Index: 959

Text #8

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1373221 (Python Code)

Max Activating Token Index: 436

Text #9

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0944. Min Act: -0.0002

Data Index: 1400923 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1396358 (Python Code)

Max Activating Token Index: 22

Text #11

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0984. Min Act: -0.0002

Data Index: 1490054 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0937. Min Act: -0.0002

Data Index: 1644535 (Python Code)

Max Activating Token Index: 41

Text #13

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1500438 (Python Code)

Max Activating Token Index: 432

Text #14

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0927. Min Act: -0.0002

Data Index: 1538254 (Python Code)

Max Activating Token Index: 633

Text #15

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1562309 (Python Code)

Max Activating Token Index: 902

Text #16

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1610279 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1491461 (Python Code)

Max Activating Token Index: 649

Text #18

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0922. Min Act: -0.0002

Data Index: 1455331 (Python Code)

Max Activating Token Index: 535

Text #19

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1393783 (Python Code)

Max Activating Token Index: 971