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

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

Neuron 5285 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.1095. Min Act: -0.0001

Data Index: 61244 (C4 (Web Text))

Max Activating Token Index: 460

Text #1

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1521628 (Python Code)

Max Activating Token Index: 887

Text #2

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0911. Min Act: -0.0001

Data Index: 118498 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0871. Min Act: -0.0001

Data Index: 272872 (C4 (Web Text))

Max Activating Token Index: 435

Text #4

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0904. Min Act: -0.0001

Data Index: 1630927 (Python Code)

Max Activating Token Index: 175

Text #5

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0967. Min Act: -0.0001

Data Index: 475367 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0955. Min Act: -0.0001

Data Index: 790939 (C4 (Web Text))

Max Activating Token Index: 426

Text #7

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0862. Min Act: -0.0001

Data Index: 1170148 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0884. Min Act: -0.0001

Data Index: 964198 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1190713 (C4 (Web Text))

Max Activating Token Index: 526

Text #10

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1096191 (C4 (Web Text))

Max Activating Token Index: 656

Text #11

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0826. Min Act: -0.0001

Data Index: 757827 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0902. Min Act: -0.0001

Data Index: 1184455 (C4 (Web Text))

Max Activating Token Index: 829

Text #13

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0890. Min Act: -0.0001

Data Index: 591006 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0894. Min Act: -0.0001

Data Index: 456736 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0916. Min Act: -0.0001

Data Index: 491359 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1379130 (Python Code)

Max Activating Token Index: 181

Text #17

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0923. Min Act: -0.0001

Data Index: 743238 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0762. Min Act: -0.0001

Data Index: 978213 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 0.1095. Min Range: -0.1095

Max Act: 0.0865. Min Act: -0.0001

Data Index: 1434673 (Python Code)

Max Activating Token Index: 401