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

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

Neuron 3190 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.7909. Min Act: -0.0001

Data Index: 1578346 (Python Code)

Max Activating Token Index: 434

Text #1

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5806. Min Act: -0.0001

Data Index: 1463152 (Python Code)

Max Activating Token Index: 649

Text #2

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5992. Min Act: -0.0001

Data Index: 1415965 (Python Code)

Max Activating Token Index: 95

Text #3

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5827. Min Act: -0.0001

Data Index: 1638385 (Python Code)

Max Activating Token Index: 233

Text #4

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6227. Min Act: -0.0001

Data Index: 1483128 (Python Code)

Max Activating Token Index: 739

Text #5

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5750. Min Act: -0.0001

Data Index: 1391686 (Python Code)

Max Activating Token Index: 368

Text #6

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5734. Min Act: -0.0001

Data Index: 1506817 (Python Code)

Max Activating Token Index: 199

Text #7

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5534. Min Act: -0.0001

Data Index: 681124 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6043. Min Act: -0.0001

Data Index: 1549770 (Python Code)

Max Activating Token Index: 666

Text #9

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1655887 (Python Code)

Max Activating Token Index: 97

Text #10

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5778. Min Act: -0.0001

Data Index: 1569062 (Python Code)

Max Activating Token Index: 139

Text #11

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5345. Min Act: -0.0001

Data Index: 1581391 (Python Code)

Max Activating Token Index: 131

Text #12

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5472. Min Act: -0.0001

Data Index: 1588829 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5628. Min Act: -0.0001

Data Index: 1401997 (Python Code)

Max Activating Token Index: 1014

Text #14

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5063. Min Act: -0.0001

Data Index: 1510596 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5397. Min Act: -0.0001

Data Index: 1548392 (Python Code)

Max Activating Token Index: 250

Text #16

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5059. Min Act: -0.0001

Data Index: 1427185 (Python Code)

Max Activating Token Index: 537

Text #17

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5261. Min Act: -0.0001

Data Index: 1542036 (Python Code)

Max Activating Token Index: 470

Text #18

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5569. Min Act: -0.0001

Data Index: 1423994 (Python Code)

Max Activating Token Index: 568

Text #19

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5246. Min Act: -0.0001

Data Index: 1497784 (Python Code)

Max Activating Token Index: 717