Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1032 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6733. Min Act: -0.0001

Data Index: 86861 (C4 (Web Text))

Max Activating Token Index: 824

Text #1

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.6217. Min Act: -0.0001

Data Index: 1084538 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5792. Min Act: -0.0001

Data Index: 731928 (C4 (Web Text))

Max Activating Token Index: 460

Text #3

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5792. Min Act: -0.0001

Data Index: 97040 (C4 (Web Text))

Max Activating Token Index: 550

Text #4

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5406. Min Act: -0.0001

Data Index: 709864 (C4 (Web Text))

Max Activating Token Index: 503

Text #5

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5404. Min Act: -0.0001

Data Index: 410572 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5471. Min Act: -0.0001

Data Index: 457576 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5431. Min Act: -0.0001

Data Index: 1200528 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5124. Min Act: -0.0001

Data Index: 454419 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4763. Min Act: -0.0001

Data Index: 70800 (C4 (Web Text))

Max Activating Token Index: 381

Text #10

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1288824 (C4 (Web Text))

Max Activating Token Index: 141

Text #11

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5006. Min Act: -0.0001

Data Index: 1356386 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4809. Min Act: -0.0001

Data Index: 342153 (C4 (Web Text))

Max Activating Token Index: 447

Text #13

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.5128. Min Act: -0.0001

Data Index: 895966 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4615. Min Act: -0.0001

Data Index: 598976 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4460. Min Act: -0.0001

Data Index: 481316 (C4 (Web Text))

Max Activating Token Index: 435

Text #16

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4569. Min Act: -0.0001

Data Index: 1173368 (C4 (Web Text))

Max Activating Token Index: 345

Text #17

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4689. Min Act: -0.0001

Data Index: 517215 (C4 (Web Text))

Max Activating Token Index: 459

Text #18

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4674. Min Act: -0.0001

Data Index: 681381 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.6733. Min Range: -0.6733

Max Act: 0.4660. Min Act: -0.0001

Data Index: 1006551 (C4 (Web Text))

Max Activating Token Index: 366