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

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

Neuron 1469 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.3908. Min Range: -8.3908

Max Act: 7.3665. Min Act: -0.0000

Data Index: 345957 (C4 (Web Text))

Max Activating Token Index: 339

Text #1

Max Range: 8.3908. Min Range: -8.3908

Max Act: 8.3908. Min Act: -0.0000

Data Index: 668536 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 8.3908. Min Range: -8.3908

Max Act: 7.7140. Min Act: -0.0000

Data Index: 218870 (C4 (Web Text))

Max Activating Token Index: 559

Text #3

Max Range: 8.3908. Min Range: -8.3908

Max Act: 7.3531. Min Act: -0.0000

Data Index: 325790 (C4 (Web Text))

Max Activating Token Index: 933

Text #4

Max Range: 8.3908. Min Range: -8.3908

Max Act: 7.2139. Min Act: -0.0000

Data Index: 524422 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 8.3908. Min Range: -8.3908

Max Act: 6.8036. Min Act: -0.0000

Data Index: 1262073 (C4 (Web Text))

Max Activating Token Index: 824

Text #6

Max Range: 8.3908. Min Range: -8.3908

Max Act: 7.1760. Min Act: -0.0000

Data Index: 496086 (C4 (Web Text))

Max Activating Token Index: 481

Text #7

Max Range: 8.3908. Min Range: -8.3908

Max Act: 6.2546. Min Act: -0.0000

Data Index: 1003365 (C4 (Web Text))

Max Activating Token Index: 676

Text #8

Max Range: 8.3908. Min Range: -8.3908

Max Act: 5.2304. Min Act: -0.0000

Data Index: 630809 (C4 (Web Text))

Max Activating Token Index: 518

Text #9

Max Range: 8.3908. Min Range: -8.3908

Max Act: 6.1375. Min Act: -0.0000

Data Index: 97881 (C4 (Web Text))

Max Activating Token Index: 164

Text #10

Max Range: 8.3908. Min Range: -8.3908

Max Act: 5.3887. Min Act: -0.0000

Data Index: 823933 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 8.3908. Min Range: -8.3908

Max Act: 6.6015. Min Act: -0.0000

Data Index: 797844 (C4 (Web Text))

Max Activating Token Index: 198

Text #12

Max Range: 8.3908. Min Range: -8.3908

Max Act: 4.1404. Min Act: -0.0000

Data Index: 351885 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 8.3908. Min Range: -8.3908

Max Act: 5.4501. Min Act: -0.0000

Data Index: 51950 (C4 (Web Text))

Max Activating Token Index: 300

Text #14

Max Range: 8.3908. Min Range: -8.3908

Max Act: 4.9800. Min Act: -0.0000

Data Index: 545066 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 8.3908. Min Range: -8.3908

Max Act: 5.0608. Min Act: -0.0000

Data Index: 208334 (C4 (Web Text))

Max Activating Token Index: 1013

Text #16

Max Range: 8.3908. Min Range: -8.3908

Max Act: 4.5222. Min Act: -0.0000

Data Index: 1307879 (C4 (Web Text))

Max Activating Token Index: 351

Text #17

Max Range: 8.3908. Min Range: -8.3908

Max Act: 4.6778. Min Act: -0.0000

Data Index: 59123 (C4 (Web Text))

Max Activating Token Index: 629

Text #18

Max Range: 8.3908. Min Range: -8.3908

Max Act: 4.6003. Min Act: -0.0000

Data Index: 957518 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 8.3908. Min Range: -8.3908

Max Act: 4.7389. Min Act: -0.0000

Data Index: 613565 (C4 (Web Text))

Max Activating Token Index: 201