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

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

Neuron 2073 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3120. Min Range: -2.3120

Max Act: 2.2195. Min Act: -0.0000

Data Index: 1467951 (Python Code)

Max Activating Token Index: 254

Text #1

Max Range: 2.3120. Min Range: -2.3120

Max Act: 2.3120. Min Act: -0.0000

Data Index: 1618366 (Python Code)

Max Activating Token Index: 979

Text #2

Max Range: 2.3120. Min Range: -2.3120

Max Act: 2.0217. Min Act: -0.0000

Data Index: 1489177 (Python Code)

Max Activating Token Index: 670

Text #3

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.9833. Min Act: -0.0000

Data Index: 73869 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.9027. Min Act: -0.0000

Data Index: 1306508 (C4 (Web Text))

Max Activating Token Index: 713

Text #5

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.9761. Min Act: -0.0000

Data Index: 1425843 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.9234. Min Act: -0.0000

Data Index: 137491 (C4 (Web Text))

Max Activating Token Index: 501

Text #7

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.9898. Min Act: -0.0000

Data Index: 1505229 (Python Code)

Max Activating Token Index: 444

Text #8

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.7518. Min Act: -0.0000

Data Index: 1464341 (Python Code)

Max Activating Token Index: 424

Text #9

Max Range: 2.3120. Min Range: -2.3120

Max Act: 2.3095. Min Act: -0.0000

Data Index: 1471806 (Python Code)

Max Activating Token Index: 399

Text #10

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.5896. Min Act: -0.0000

Data Index: 518511 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.4434. Min Act: -0.0000

Data Index: 1553084 (Python Code)

Max Activating Token Index: 881

Text #12

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.6474. Min Act: -0.0000

Data Index: 1432635 (Python Code)

Max Activating Token Index: 663

Text #13

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.4666. Min Act: -0.0000

Data Index: 1631312 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.5072. Min Act: -0.0000

Data Index: 830489 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.7143. Min Act: -0.0000

Data Index: 1451950 (Python Code)

Max Activating Token Index: 300

Text #16

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.3941. Min Act: -0.0000

Data Index: 152461 (C4 (Web Text))

Max Activating Token Index: 811

Text #17

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1582835 (Python Code)

Max Activating Token Index: 920

Text #18

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.5386. Min Act: -0.0000

Data Index: 1626302 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 2.3120. Min Range: -2.3120

Max Act: 1.3618. Min Act: -0.0000

Data Index: 709826 (C4 (Web Text))

Max Activating Token Index: 272