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

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

Neuron 4320 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.6701. Min Act: -0.0001

Data Index: 990461 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.6225. Min Act: -0.0001

Data Index: 1486229 (Python Code)

Max Activating Token Index: 91

Text #2

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5652. Min Act: -0.0001

Data Index: 677057 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5768. Min Act: -0.0001

Data Index: 1434180 (Python Code)

Max Activating Token Index: 76

Text #4

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5005. Min Act: -0.0001

Data Index: 335110 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4651. Min Act: -0.0001

Data Index: 473077 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5092. Min Act: -0.0001

Data Index: 1619201 (Python Code)

Max Activating Token Index: 533

Text #7

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5077. Min Act: -0.0001

Data Index: 676334 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5036. Min Act: -0.0001

Data Index: 14434 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5005. Min Act: -0.0001

Data Index: 1554839 (Python Code)

Max Activating Token Index: 568

Text #10

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4951. Min Act: -0.0001

Data Index: 991385 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4924. Min Act: -0.0001

Data Index: 1239419 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4716. Min Act: -0.0001

Data Index: 624838 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4392. Min Act: -0.0001

Data Index: 269537 (C4 (Web Text))

Max Activating Token Index: 565

Text #14

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.5209. Min Act: -0.0001

Data Index: 170482 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4682. Min Act: -0.0001

Data Index: 105410 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4658. Min Act: -0.0001

Data Index: 199381 (C4 (Web Text))

Max Activating Token Index: 937

Text #17

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4787. Min Act: -0.0001

Data Index: 653806 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4769. Min Act: -0.0001

Data Index: 1424444 (Python Code)

Max Activating Token Index: 12

Text #19

Max Range: 0.6701. Min Range: -0.6701

Max Act: 0.4454. Min Act: -0.0001

Data Index: 838755 (C4 (Web Text))

Max Activating Token Index: 167