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

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

Neuron 5108 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4877. Min Act: 0.0001

Data Index: 1560959 (Python Code)

Max Activating Token Index: 874

Text #1

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4841. Min Act: 0.0001

Data Index: 1538881 (Python Code)

Max Activating Token Index: 698

Text #2

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4635. Min Act: 0.0002

Data Index: 1586150 (Python Code)

Max Activating Token Index: 637

Text #3

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4452. Min Act: 0.0000

Data Index: 1464006 (Python Code)

Max Activating Token Index: 529

Text #4

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4285. Min Act: 0.0003

Data Index: 1389792 (Python Code)

Max Activating Token Index: 785

Text #5

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4535. Min Act: 0.0001

Data Index: 1369349 (Python Code)

Max Activating Token Index: 767

Text #6

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4467. Min Act: 0.0001

Data Index: 1500322 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4375. Min Act: 0.0000

Data Index: 1605550 (Python Code)

Max Activating Token Index: 940

Text #8

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4456. Min Act: -0.0000

Data Index: 1525043 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4412. Min Act: 0.0001

Data Index: 1460667 (Python Code)

Max Activating Token Index: 749

Text #10

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4309. Min Act: 0.0001

Data Index: 1654212 (Python Code)

Max Activating Token Index: 62

Text #11

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4305. Min Act: -0.0000

Data Index: 1597785 (Python Code)

Max Activating Token Index: 958

Text #12

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4406. Min Act: 0.0001

Data Index: 1532864 (Python Code)

Max Activating Token Index: 775

Text #13

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4045. Min Act: -0.0000

Data Index: 1586379 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4304. Min Act: 0.0001

Data Index: 1372932 (Python Code)

Max Activating Token Index: 733

Text #15

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4483. Min Act: 0.0001

Data Index: 1648757 (Python Code)

Max Activating Token Index: 526

Text #16

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4016. Min Act: 0.0000

Data Index: 1451391 (Python Code)

Max Activating Token Index: 659

Text #17

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4382. Min Act: 0.0001

Data Index: 1527424 (Python Code)

Max Activating Token Index: 765

Text #18

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4061. Min Act: 0.0001

Data Index: 1565037 (Python Code)

Max Activating Token Index: 679

Text #19

Max Range: 0.4877. Min Range: -0.4877

Max Act: 0.4224. Min Act: -0.0000

Data Index: 1625586 (Python Code)

Max Activating Token Index: 50