Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1219 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1395. Min Act: -0.0002

Data Index: 1319260 (C4 (Web Text))

Max Activating Token Index: 300

Text #1

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1121. Min Act: -0.0002

Data Index: 451301 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.1015. Min Act: -0.0002

Data Index: 120429 (C4 (Web Text))

Max Activating Token Index: 558

Text #3

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0981. Min Act: -0.0002

Data Index: 347298 (C4 (Web Text))

Max Activating Token Index: 902

Text #4

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0954. Min Act: -0.0002

Data Index: 1073705 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0870. Min Act: -0.0002

Data Index: 156417 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0947. Min Act: -0.0002

Data Index: 958344 (C4 (Web Text))

Max Activating Token Index: 587

Text #7

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0870. Min Act: -0.0002

Data Index: 949009 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0899. Min Act: -0.0002

Data Index: 1085721 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0787. Min Act: -0.0002

Data Index: 583920 (C4 (Web Text))

Max Activating Token Index: 631

Text #10

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0855. Min Act: -0.0002

Data Index: 1554619 (Python Code)

Max Activating Token Index: 838

Text #11

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0793. Min Act: -0.0002

Data Index: 1323215 (C4 (Web Text))

Max Activating Token Index: 854

Text #12

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0869. Min Act: -0.0002

Data Index: 838002 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0733. Min Act: -0.0002

Data Index: 1413727 (Python Code)

Max Activating Token Index: 856

Text #14

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0710. Min Act: -0.0002

Data Index: 989346 (C4 (Web Text))

Max Activating Token Index: 988

Text #15

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0736. Min Act: -0.0001

Data Index: 442010 (C4 (Web Text))

Max Activating Token Index: 855

Text #16

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0730. Min Act: -0.0002

Data Index: 238044 (C4 (Web Text))

Max Activating Token Index: 625

Text #17

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0782. Min Act: -0.0002

Data Index: 293651 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0740. Min Act: -0.0002

Data Index: 784607 (C4 (Web Text))

Max Activating Token Index: 720

Text #19

Max Range: 0.1395. Min Range: -0.1395

Max Act: 0.0720. Min Act: -0.0002

Data Index: 146239 (C4 (Web Text))

Max Activating Token Index: 985