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

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

Neuron 5955 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: 3.1874. Min Range: -3.1874

Max Act: 3.1874. Min Act: -0.0000

Data Index: 603885 (C4 (Web Text))

Max Activating Token Index: 977

Text #1

Max Range: 3.1874. Min Range: -3.1874

Max Act: 3.0495. Min Act: -0.0000

Data Index: 314145 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.7486. Min Act: -0.0000

Data Index: 39425 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.7049. Min Act: -0.0000

Data Index: 495772 (C4 (Web Text))

Max Activating Token Index: 342

Text #4

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.5959. Min Act: -0.0000

Data Index: 1003605 (C4 (Web Text))

Max Activating Token Index: 317

Text #5

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.4260. Min Act: -0.0000

Data Index: 77705 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.5467. Min Act: -0.0000

Data Index: 432673 (C4 (Web Text))

Max Activating Token Index: 484

Text #7

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.5320. Min Act: -0.0000

Data Index: 766552 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.5160. Min Act: -0.0000

Data Index: 413155 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.4922. Min Act: -0.0000

Data Index: 760192 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.4962. Min Act: -0.0000

Data Index: 306830 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.4923. Min Act: -0.0000

Data Index: 1346453 (C4 (Web Text))

Max Activating Token Index: 835

Text #12

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.4218. Min Act: 0.0000

Data Index: 976372 (C4 (Web Text))

Max Activating Token Index: 800

Text #13

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.3906. Min Act: -0.0000

Data Index: 642684 (C4 (Web Text))

Max Activating Token Index: 773

Text #14

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.3771. Min Act: -0.0000

Data Index: 239338 (C4 (Web Text))

Max Activating Token Index: 491

Text #15

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.3539. Min Act: 0.0000

Data Index: 1081483 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.1943. Min Act: -0.0000

Data Index: 281605 (C4 (Web Text))

Max Activating Token Index: 333

Text #17

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.1646. Min Act: -0.0000

Data Index: 1099854 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.2348. Min Act: 0.0000

Data Index: 418816 (C4 (Web Text))

Max Activating Token Index: 785

Text #19

Max Range: 3.1874. Min Range: -3.1874

Max Act: 2.2586. Min Act: -0.0000

Data Index: 143480 (C4 (Web Text))

Max Activating Token Index: 485