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

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

Neuron 3678 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: 2.4819. Min Range: -2.4819

Max Act: 2.4819. Min Act: -0.0000

Data Index: 308950 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 2.4819. Min Range: -2.4819

Max Act: 1.4219. Min Act: -0.0000

Data Index: 1249934 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 2.4819. Min Range: -2.4819

Max Act: 1.2688. Min Act: -0.0000

Data Index: 1004682 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 2.4819. Min Range: -2.4819

Max Act: 1.2856. Min Act: -0.0000

Data Index: 1584886 (Python Code)

Max Activating Token Index: 631

Text #4

Max Range: 2.4819. Min Range: -2.4819

Max Act: 1.1536. Min Act: -0.0000

Data Index: 824713 (C4 (Web Text))

Max Activating Token Index: 745

Text #5

Max Range: 2.4819. Min Range: -2.4819

Max Act: 1.0197. Min Act: -0.0000

Data Index: 1278078 (C4 (Web Text))

Max Activating Token Index: 1017

Text #6

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9548. Min Act: -0.0000

Data Index: 907292 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9731. Min Act: -0.0000

Data Index: 1092453 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9331. Min Act: -0.0000

Data Index: 608031 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9298. Min Act: -0.0000

Data Index: 91950 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9459. Min Act: -0.0000

Data Index: 419173 (C4 (Web Text))

Max Activating Token Index: 567

Text #11

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9262. Min Act: -0.0000

Data Index: 1281828 (C4 (Web Text))

Max Activating Token Index: 720

Text #12

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9077. Min Act: -0.0000

Data Index: 344697 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.8978. Min Act: -0.0000

Data Index: 381102 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.8906. Min Act: -0.0000

Data Index: 251047 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.8255. Min Act: -0.0000

Data Index: 169319 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.8669. Min Act: -0.0000

Data Index: 1566186 (Python Code)

Max Activating Token Index: 756

Text #17

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.8733. Min Act: -0.0000

Data Index: 929146 (C4 (Web Text))

Max Activating Token Index: 89

Text #18

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.8427. Min Act: -0.0000

Data Index: 622952 (C4 (Web Text))

Max Activating Token Index: 975

Text #19

Max Range: 2.4819. Min Range: -2.4819

Max Act: 0.9200. Min Act: -0.0000

Data Index: 881061 (C4 (Web Text))

Max Activating Token Index: 188