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

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

Neuron 4622 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.4701. Min Act: -0.0000

Data Index: 581002 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.3784. Min Act: -0.0000

Data Index: 460756 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.3383. Min Act: -0.0000

Data Index: 683851 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.2367. Min Act: -0.0000

Data Index: 1150244 (C4 (Web Text))

Max Activating Token Index: 954

Text #4

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.2444. Min Act: -0.0000

Data Index: 212487 (C4 (Web Text))

Max Activating Token Index: 19

Text #5

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.0939. Min Act: -0.0000

Data Index: 955288 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.1700. Min Act: -0.0000

Data Index: 1189430 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.1721. Min Act: -0.0000

Data Index: 1351232 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.1671. Min Act: -0.0000

Data Index: 825157 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.1535. Min Act: -0.0000

Data Index: 687776 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.1400. Min Act: -0.0000

Data Index: 742309 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.1115. Min Act: -0.0000

Data Index: 457601 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.2009. Min Act: -0.0000

Data Index: 1137952 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.0841. Min Act: -0.0000

Data Index: 397783 (C4 (Web Text))

Max Activating Token Index: 735

Text #14

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.0811. Min Act: -0.0000

Data Index: 730185 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.0930. Min Act: -0.0000

Data Index: 305204 (C4 (Web Text))

Max Activating Token Index: 873

Text #16

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.0719. Min Act: -0.0000

Data Index: 406573 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.1482. Min Act: -0.0000

Data Index: 1186549 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.0097. Min Act: -0.0000

Data Index: 1262936 (C4 (Web Text))

Max Activating Token Index: 879

Text #19

Max Range: 2.4701. Min Range: -2.4701

Max Act: 2.0110. Min Act: -0.0000

Data Index: 1046727 (C4 (Web Text))

Max Activating Token Index: 610