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

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

Neuron 2493 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6916. Min Act: -0.0000

Data Index: 1155699 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6000. Min Act: -0.0000

Data Index: 106542 (C4 (Web Text))

Max Activating Token Index: 888

Text #2

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5968. Min Act: -0.0000

Data Index: 1050750 (C4 (Web Text))

Max Activating Token Index: 461

Text #3

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5977. Min Act: -0.0000

Data Index: 725291 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5992. Min Act: -0.0000

Data Index: 755799 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.6285. Min Act: -0.0000

Data Index: 977049 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1257022 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1278802 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5402. Min Act: -0.0000

Data Index: 860539 (C4 (Web Text))

Max Activating Token Index: 631

Text #9

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4870. Min Act: -0.0000

Data Index: 35831 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1377951 (Python Code)

Max Activating Token Index: 735

Text #11

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5583. Min Act: -0.0000

Data Index: 704617 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5260. Min Act: -0.0000

Data Index: 107367 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5496. Min Act: -0.0000

Data Index: 1467481 (Python Code)

Max Activating Token Index: 701

Text #14

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5136. Min Act: -0.0000

Data Index: 63220 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5423. Min Act: -0.0000

Data Index: 537848 (C4 (Web Text))

Max Activating Token Index: 762

Text #16

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.5000. Min Act: -0.0000

Data Index: 549973 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4846. Min Act: -0.0000

Data Index: 742722 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4622. Min Act: -0.0000

Data Index: 1198611 (C4 (Web Text))

Max Activating Token Index: 613

Text #19

Max Range: 0.6916. Min Range: -0.6916

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1121568 (C4 (Web Text))

Max Activating Token Index: 345