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

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

Neuron 439 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: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0002

Data Index: 1437055 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1584923 (Python Code)

Max Activating Token Index: 9

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1653809 (Python Code)

Max Activating Token Index: 4

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1079. Min Act: -0.0002

Data Index: 1443605 (Python Code)

Max Activating Token Index: 9

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1085. Min Act: -0.0002

Data Index: 1594778 (Python Code)

Max Activating Token Index: 4

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1599630 (Python Code)

Max Activating Token Index: 3

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1599826 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1514056 (Python Code)

Max Activating Token Index: 4

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1522876 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1008. Min Act: -0.0002

Data Index: 1558520 (Python Code)

Max Activating Token Index: 9

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1466971 (Python Code)

Max Activating Token Index: 3

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1633170 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0942. Min Act: -0.0002

Data Index: 1477482 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0969. Min Act: -0.0002

Data Index: 1432218 (Python Code)

Max Activating Token Index: 3

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1544327 (Python Code)

Max Activating Token Index: 7

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1499858 (Python Code)

Max Activating Token Index: 9

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1636678 (Python Code)

Max Activating Token Index: 8

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1466824 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1361203 (Python Code)

Max Activating Token Index: 8

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0898. Min Act: -0.0002

Data Index: 1443453 (Python Code)

Max Activating Token Index: 8