Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4732 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.7616. Min Range: -1.7616

Max Act: 1.7616. Min Act: -0.0000

Data Index: 1459240 (Python Code)

Max Activating Token Index: 858

Text #1

Max Range: 1.7616. Min Range: -1.7616

Max Act: 1.1452. Min Act: -0.0000

Data Index: 296329 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 1.7616. Min Range: -1.7616

Max Act: 1.0410. Min Act: 0.0000

Data Index: 624041 (C4 (Web Text))

Max Activating Token Index: 845

Text #3

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.9675. Min Act: -0.0000

Data Index: 1325784 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.9926. Min Act: -0.0000

Data Index: 378845 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.9841. Min Act: -0.0000

Data Index: 1429422 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.9735. Min Act: 0.0000

Data Index: 614752 (C4 (Web Text))

Max Activating Token Index: 210

Text #7

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.9526. Min Act: -0.0000

Data Index: 803446 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.8520. Min Act: -0.0000

Data Index: 666048 (C4 (Web Text))

Max Activating Token Index: 854

Text #9

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.9066. Min Act: -0.0000

Data Index: 564798 (C4 (Web Text))

Max Activating Token Index: 151

Text #10

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.8610. Min Act: -0.0000

Data Index: 1210791 (C4 (Web Text))

Max Activating Token Index: 718

Text #11

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.8528. Min Act: -0.0000

Data Index: 631722 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.8594. Min Act: 0.0000

Data Index: 480654 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.7793. Min Act: -0.0000

Data Index: 452484 (C4 (Web Text))

Max Activating Token Index: 979

Text #14

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.7871. Min Act: 0.0000

Data Index: 144784 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.7831. Min Act: -0.0000

Data Index: 548113 (C4 (Web Text))

Max Activating Token Index: 376

Text #16

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.7817. Min Act: -0.0000

Data Index: 741383 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.7818. Min Act: 0.0000

Data Index: 392395 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.7429. Min Act: -0.0000

Data Index: 1115998 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 1.7616. Min Range: -1.7616

Max Act: 0.7917. Min Act: -0.0000

Data Index: 762926 (C4 (Web Text))

Max Activating Token Index: 677