Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 236 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.5079. Min Act: -0.0000

Data Index: 1215905 (C4 (Web Text))

Max Activating Token Index: 176

Text #1

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4941. Min Act: -0.0000

Data Index: 875130 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4868. Min Act: -0.0000

Data Index: 322950 (C4 (Web Text))

Max Activating Token Index: 603

Text #3

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4443. Min Act: -0.0000

Data Index: 916003 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.4556. Min Act: -0.0000

Data Index: 528238 (C4 (Web Text))

Max Activating Token Index: 293

Text #5

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1409861 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3905. Min Act: -0.0000

Data Index: 1035627 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3889. Min Act: -0.0001

Data Index: 1619443 (Python Code)

Max Activating Token Index: 923

Text #8

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3860. Min Act: -0.0000

Data Index: 1443757 (Python Code)

Max Activating Token Index: 634

Text #9

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3782. Min Act: -0.0000

Data Index: 101655 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1375918 (Python Code)

Max Activating Token Index: 538

Text #11

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3529. Min Act: -0.0001

Data Index: 1439058 (Python Code)

Max Activating Token Index: 171

Text #12

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3762. Min Act: -0.0001

Data Index: 1515145 (Python Code)

Max Activating Token Index: 338

Text #13

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3335. Min Act: -0.0000

Data Index: 1605826 (Python Code)

Max Activating Token Index: 118

Text #14

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3565. Min Act: -0.0001

Data Index: 1617737 (Python Code)

Max Activating Token Index: 81

Text #15

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3412. Min Act: 0.0000

Data Index: 1476066 (Python Code)

Max Activating Token Index: 814

Text #16

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3517. Min Act: -0.0000

Data Index: 1453567 (Python Code)

Max Activating Token Index: 317

Text #17

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3326. Min Act: -0.0001

Data Index: 1507374 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3413. Min Act: -0.0000

Data Index: 997703 (C4 (Web Text))

Max Activating Token Index: 177

Text #19

Max Range: 0.5079. Min Range: -0.5079

Max Act: 0.3261. Min Act: -0.0000

Data Index: 158682 (C4 (Web Text))

Max Activating Token Index: 816