Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2902 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 5.2901. Min Range: -5.2901

Max Act: 5.2901. Min Act: 0.0000

Data Index: 1610912 (Python Code)

Max Activating Token Index: 885

Text #1

Max Range: 5.2901. Min Range: -5.2901

Max Act: 4.8144. Min Act: -0.0000

Data Index: 1525806 (Python Code)

Max Activating Token Index: 271

Text #2

Max Range: 5.2901. Min Range: -5.2901

Max Act: 4.3687. Min Act: -0.0000

Data Index: 1531717 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 5.2901. Min Range: -5.2901

Max Act: 3.5446. Min Act: 0.0000

Data Index: 1482006 (Python Code)

Max Activating Token Index: 913

Text #4

Max Range: 5.2901. Min Range: -5.2901

Max Act: 3.2337. Min Act: -0.0000

Data Index: 1586639 (Python Code)

Max Activating Token Index: 579

Text #5

Max Range: 5.2901. Min Range: -5.2901

Max Act: 3.0207. Min Act: -0.0000

Data Index: 1614406 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.8162. Min Act: 0.0000

Data Index: 1410408 (Python Code)

Max Activating Token Index: 242

Text #7

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.9490. Min Act: -0.0000

Data Index: 1523182 (Python Code)

Max Activating Token Index: 125

Text #8

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.8004. Min Act: 0.0000

Data Index: 1601415 (Python Code)

Max Activating Token Index: 444

Text #9

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.6406. Min Act: 0.0000

Data Index: 1549207 (Python Code)

Max Activating Token Index: 978

Text #10

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.4642. Min Act: -0.0000

Data Index: 1372651 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.5590. Min Act: -0.0000

Data Index: 1555166 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.5374. Min Act: -0.0000

Data Index: 1603696 (Python Code)

Max Activating Token Index: 54

Text #13

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.4706. Min Act: 0.0000

Data Index: 1424529 (Python Code)

Max Activating Token Index: 80

Text #14

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.4443. Min Act: 0.0000

Data Index: 1428372 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.3989. Min Act: 0.0000

Data Index: 1626394 (Python Code)

Max Activating Token Index: 65

Text #16

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.2098. Min Act: -0.0000

Data Index: 1448314 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.4628. Min Act: -0.0000

Data Index: 1431765 (Python Code)

Max Activating Token Index: 306

Text #18

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.3273. Min Act: 0.0000

Data Index: 1538915 (Python Code)

Max Activating Token Index: 196

Text #19

Max Range: 5.2901. Min Range: -5.2901

Max Act: 2.3091. Min Act: 0.0000

Data Index: 1649775 (Python Code)

Max Activating Token Index: 513