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

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

Neuron 1205 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.6010. Min Act: -0.0000

Data Index: 205138 (C4 (Web Text))

Max Activating Token Index: 537

Text #1

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1552262 (Python Code)

Max Activating Token Index: 147

Text #2

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5108. Min Act: -0.0000

Data Index: 681509 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4628. Min Act: -0.0000

Data Index: 1653908 (Python Code)

Max Activating Token Index: 846

Text #4

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1482394 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4952. Min Act: -0.0000

Data Index: 909018 (C4 (Web Text))

Max Activating Token Index: 994

Text #6

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4881. Min Act: -0.0000

Data Index: 1544024 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1541373 (Python Code)

Max Activating Token Index: 9

Text #8

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4893. Min Act: -0.0000

Data Index: 1062265 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4985. Min Act: -0.0000

Data Index: 158427 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4899. Min Act: -0.0000

Data Index: 743876 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1634246 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4549. Min Act: -0.0000

Data Index: 929072 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.5123. Min Act: -0.0001

Data Index: 1629571 (Python Code)

Max Activating Token Index: 188

Text #14

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1629997 (Python Code)

Max Activating Token Index: 922

Text #15

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4770. Min Act: -0.0000

Data Index: 1652435 (Python Code)

Max Activating Token Index: 956

Text #16

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4293. Min Act: -0.0000

Data Index: 513516 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4935. Min Act: -0.0000

Data Index: 1533724 (Python Code)

Max Activating Token Index: 731

Text #18

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1655338 (Python Code)

Max Activating Token Index: 768

Text #19

Max Range: 0.6010. Min Range: -0.6010

Max Act: 0.4516. Min Act: -0.0000

Data Index: 1501134 (Python Code)

Max Activating Token Index: 688