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

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

Neuron 96 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6974. Min Act: -0.0000

Data Index: 1016042 (C4 (Web Text))

Max Activating Token Index: 909

Text #1

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6739. Min Act: -0.0000

Data Index: 1438856 (Python Code)

Max Activating Token Index: 401

Text #2

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6403. Min Act: -0.0000

Data Index: 85494 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6369. Min Act: -0.0000

Data Index: 303685 (C4 (Web Text))

Max Activating Token Index: 614

Text #4

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6289. Min Act: -0.0000

Data Index: 3787 (C4 (Web Text))

Max Activating Token Index: 990

Text #5

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6494. Min Act: -0.0000

Data Index: 421938 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1520305 (Python Code)

Max Activating Token Index: 904

Text #7

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6255. Min Act: -0.0000

Data Index: 1038741 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6380. Min Act: -0.0000

Data Index: 1625400 (Python Code)

Max Activating Token Index: 387

Text #9

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1433626 (Python Code)

Max Activating Token Index: 188

Text #10

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6299. Min Act: -0.0000

Data Index: 1536987 (Python Code)

Max Activating Token Index: 644

Text #11

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6517. Min Act: -0.0000

Data Index: 1641097 (Python Code)

Max Activating Token Index: 818

Text #12

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6345. Min Act: -0.0000

Data Index: 1380445 (Python Code)

Max Activating Token Index: 577

Text #13

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6048. Min Act: -0.0000

Data Index: 1558562 (Python Code)

Max Activating Token Index: 208

Text #14

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6148. Min Act: -0.0000

Data Index: 1543632 (Python Code)

Max Activating Token Index: 717

Text #15

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1591821 (Python Code)

Max Activating Token Index: 661

Text #16

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5965. Min Act: -0.0000

Data Index: 1606525 (Python Code)

Max Activating Token Index: 628

Text #17

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5853. Min Act: -0.0000

Data Index: 1651342 (Python Code)

Max Activating Token Index: 887

Text #18

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.6264. Min Act: -0.0000

Data Index: 1473965 (Python Code)

Max Activating Token Index: 580

Text #19

Max Range: 0.6974. Min Range: -0.6974

Max Act: 0.5929. Min Act: -0.0000

Data Index: 1539603 (Python Code)

Max Activating Token Index: 682