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

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

Neuron 1192 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: 1.2777. Min Range: -1.2777

Max Act: 1.2777. Min Act: -0.0000

Data Index: 964769 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1493. Min Act: -0.0000

Data Index: 854949 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1658. Min Act: -0.0000

Data Index: 821883 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1937. Min Act: -0.0000

Data Index: 483060 (C4 (Web Text))

Max Activating Token Index: 566

Text #4

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1599. Min Act: -0.0000

Data Index: 321477 (C4 (Web Text))

Max Activating Token Index: 620

Text #5

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0393. Min Act: -0.0000

Data Index: 733527 (C4 (Web Text))

Max Activating Token Index: 666

Text #6

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.1327. Min Act: -0.0000

Data Index: 1331238 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0366. Min Act: -0.0000

Data Index: 518404 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0810. Min Act: -0.0000

Data Index: 299018 (C4 (Web Text))

Max Activating Token Index: 651

Text #9

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0306. Min Act: -0.0000

Data Index: 914689 (C4 (Web Text))

Max Activating Token Index: 39

Text #10

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1322888 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0109. Min Act: -0.0000

Data Index: 451456 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0472. Min Act: -0.0000

Data Index: 956865 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0317. Min Act: -0.0000

Data Index: 111408 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9698. Min Act: -0.0000

Data Index: 134301 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9202. Min Act: -0.0000

Data Index: 770831 (C4 (Web Text))

Max Activating Token Index: 381

Text #16

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9923. Min Act: -0.0000

Data Index: 1096021 (C4 (Web Text))

Max Activating Token Index: 454

Text #17

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0050. Min Act: -0.0000

Data Index: 777713 (C4 (Web Text))

Max Activating Token Index: 365

Text #18

Max Range: 1.2777. Min Range: -1.2777

Max Act: 0.9464. Min Act: -0.0000

Data Index: 556508 (C4 (Web Text))

Max Activating Token Index: 361

Text #19

Max Range: 1.2777. Min Range: -1.2777

Max Act: 1.0163. Min Act: -0.0000

Data Index: 636601 (C4 (Web Text))

Max Activating Token Index: 143