Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1263 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6948. Min Act: -0.0000

Data Index: 1483990 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.6172. Min Act: -0.0001

Data Index: 1616830 (Python Code)

Max Activating Token Index: 129

Text #2

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1597497 (Python Code)

Max Activating Token Index: 888

Text #3

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5614. Min Act: -0.0001

Data Index: 1427508 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5396. Min Act: -0.0001

Data Index: 1508032 (Python Code)

Max Activating Token Index: 786

Text #5

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1640670 (Python Code)

Max Activating Token Index: 240

Text #6

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1542782 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5115. Min Act: -0.0001

Data Index: 1533732 (Python Code)

Max Activating Token Index: 548

Text #8

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1453514 (Python Code)

Max Activating Token Index: 300

Text #9

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5310. Min Act: -0.0001

Data Index: 1429787 (Python Code)

Max Activating Token Index: 116

Text #10

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5066. Min Act: -0.0000

Data Index: 1455661 (Python Code)

Max Activating Token Index: 690

Text #11

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5230. Min Act: -0.0000

Data Index: 1632299 (Python Code)

Max Activating Token Index: 466

Text #12

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5031. Min Act: -0.0001

Data Index: 1452333 (Python Code)

Max Activating Token Index: 956

Text #13

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5039. Min Act: -0.0001

Data Index: 1557603 (Python Code)

Max Activating Token Index: 957

Text #14

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4832. Min Act: -0.0000

Data Index: 1546897 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4810. Min Act: -0.0000

Data Index: 1420598 (Python Code)

Max Activating Token Index: 211

Text #16

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4778. Min Act: -0.0001

Data Index: 1393181 (Python Code)

Max Activating Token Index: 55

Text #17

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4943. Min Act: -0.0001

Data Index: 1562435 (Python Code)

Max Activating Token Index: 172

Text #18

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1500817 (Python Code)

Max Activating Token Index: 983

Text #19

Max Range: 0.6948. Min Range: -0.6948

Max Act: 0.4777. Min Act: -0.0001

Data Index: 1646595 (Python Code)

Max Activating Token Index: 96