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

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

Neuron 3985 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.1588. Min Act: -0.0002

Data Index: 257412 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.1604. Min Act: -0.0002

Data Index: 1260513 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 1.1604. Min Range: -1.1604

Max Act: 1.0229. Min Act: -0.0002

Data Index: 148985 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.7996. Min Act: -0.0002

Data Index: 647950 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8977. Min Act: -0.0002

Data Index: 1090059 (C4 (Web Text))

Max Activating Token Index: 93

Text #5

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9707. Min Act: -0.0001

Data Index: 1145470 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9486. Min Act: -0.0001

Data Index: 541244 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9658. Min Act: -0.0002

Data Index: 424985 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9276. Min Act: -0.0002

Data Index: 687351 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8987. Min Act: -0.0002

Data Index: 365431 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9580. Min Act: -0.0002

Data Index: 135361 (C4 (Web Text))

Max Activating Token Index: 241

Text #11

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8198. Min Act: -0.0002

Data Index: 27529 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8493. Min Act: -0.0002

Data Index: 843723 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8719. Min Act: -0.0001

Data Index: 699168 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8710. Min Act: -0.0001

Data Index: 753446 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8374. Min Act: -0.0001

Data Index: 501309 (C4 (Web Text))

Max Activating Token Index: 414

Text #16

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.9471. Min Act: -0.0001

Data Index: 255453 (C4 (Web Text))

Max Activating Token Index: 348

Text #17

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.7931. Min Act: -0.0002

Data Index: 433986 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8902. Min Act: -0.0002

Data Index: 1217553 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 1.1604. Min Range: -1.1604

Max Act: 0.8658. Min Act: -0.0001

Data Index: 1008930 (C4 (Web Text))

Max Activating Token Index: 136