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

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

Neuron 5419 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.4968. Min Act: -0.0000

Data Index: 869220 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.2339. Min Act: -0.0000

Data Index: 468201 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.3036. Min Act: -0.0000

Data Index: 1516061 (Python Code)

Max Activating Token Index: 1011

Text #3

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.1508. Min Act: 0.0000

Data Index: 212673 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.0852. Min Act: -0.0000

Data Index: 1376865 (Python Code)

Max Activating Token Index: 1020

Text #5

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.9430. Min Act: -0.0000

Data Index: 1430488 (Python Code)

Max Activating Token Index: 278

Text #6

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.0637. Min Act: -0.0000

Data Index: 910943 (C4 (Web Text))

Max Activating Token Index: 51

Text #7

Max Range: 1.4968. Min Range: -1.4968

Max Act: 1.0399. Min Act: -0.0000

Data Index: 548887 (C4 (Web Text))

Max Activating Token Index: 423

Text #8

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.9631. Min Act: -0.0000

Data Index: 63013 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1500500 (Python Code)

Max Activating Token Index: 820

Text #10

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1485587 (Python Code)

Max Activating Token Index: 645

Text #11

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8985. Min Act: -0.0000

Data Index: 1108028 (C4 (Web Text))

Max Activating Token Index: 376

Text #12

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1132200 (C4 (Web Text))

Max Activating Token Index: 945

Text #13

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8849. Min Act: -0.0000

Data Index: 229597 (C4 (Web Text))

Max Activating Token Index: 56

Text #14

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8819. Min Act: -0.0000

Data Index: 507863 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1551716 (Python Code)

Max Activating Token Index: 948

Text #16

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8257. Min Act: -0.0000

Data Index: 1431893 (Python Code)

Max Activating Token Index: 445

Text #17

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8950. Min Act: -0.0000

Data Index: 1401171 (Python Code)

Max Activating Token Index: 904

Text #18

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1302097 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.4968. Min Range: -1.4968

Max Act: 0.8109. Min Act: -0.0000

Data Index: 1573814 (Python Code)

Max Activating Token Index: 1023