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

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

Neuron 1972 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: 0.2492. Min Range: -0.2492

Max Act: 0.2492. Min Act: -0.0000

Data Index: 266321 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2338. Min Act: -0.0000

Data Index: 374273 (C4 (Web Text))

Max Activating Token Index: 555

Text #2

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2234. Min Act: -0.0000

Data Index: 849851 (C4 (Web Text))

Max Activating Token Index: 578

Text #3

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2427. Min Act: -0.0000

Data Index: 116087 (C4 (Web Text))

Max Activating Token Index: 734

Text #4

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2328. Min Act: -0.0000

Data Index: 9356 (C4 (Web Text))

Max Activating Token Index: 210

Text #5

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1242085 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1197950 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1778. Min Act: -0.0000

Data Index: 255817 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2002. Min Act: -0.0000

Data Index: 742562 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1999. Min Act: -0.0000

Data Index: 505792 (C4 (Web Text))

Max Activating Token Index: 298

Text #10

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1673. Min Act: -0.0000

Data Index: 585613 (C4 (Web Text))

Max Activating Token Index: 212

Text #11

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.2016. Min Act: -0.0000

Data Index: 548053 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1974. Min Act: -0.0000

Data Index: 827766 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1900. Min Act: -0.0000

Data Index: 713066 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1722. Min Act: -0.0000

Data Index: 886280 (C4 (Web Text))

Max Activating Token Index: 904

Text #15

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1048735 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1890. Min Act: -0.0000

Data Index: 338597 (C4 (Web Text))

Max Activating Token Index: 154

Text #17

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1763. Min Act: -0.0000

Data Index: 407615 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1774. Min Act: -0.0000

Data Index: 566360 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.2492. Min Range: -0.2492

Max Act: 0.1769. Min Act: -0.0000

Data Index: 925440 (C4 (Web Text))

Max Activating Token Index: 853