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

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

Neuron 1472 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.8843. Min Act: -0.0001

Data Index: 1063784 (C4 (Web Text))

Max Activating Token Index: 98

Text #1

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.8546. Min Act: -0.0001

Data Index: 340527 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.8041. Min Act: -0.0001

Data Index: 598526 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.7985. Min Act: -0.0001

Data Index: 319376 (C4 (Web Text))

Max Activating Token Index: 413

Text #4

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.7757. Min Act: -0.0001

Data Index: 501256 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.7280. Min Act: -0.0001

Data Index: 481669 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6986. Min Act: -0.0001

Data Index: 661180 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6148. Min Act: -0.0001

Data Index: 212025 (C4 (Web Text))

Max Activating Token Index: 202

Text #8

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6341. Min Act: -0.0000

Data Index: 73044 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6802. Min Act: -0.0001

Data Index: 316930 (C4 (Web Text))

Max Activating Token Index: 610

Text #10

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6391. Min Act: -0.0001

Data Index: 1005970 (C4 (Web Text))

Max Activating Token Index: 755

Text #11

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6002. Min Act: -0.0001

Data Index: 776709 (C4 (Web Text))

Max Activating Token Index: 297

Text #12

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6709. Min Act: -0.0001

Data Index: 466958 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6295. Min Act: -0.0001

Data Index: 1331384 (C4 (Web Text))

Max Activating Token Index: 578

Text #14

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6389. Min Act: -0.0001

Data Index: 1202398 (C4 (Web Text))

Max Activating Token Index: 75

Text #15

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.5790. Min Act: -0.0001

Data Index: 210607 (C4 (Web Text))

Max Activating Token Index: 155

Text #16

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6718. Min Act: -0.0000

Data Index: 909455 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6401. Min Act: -0.0001

Data Index: 1310600 (C4 (Web Text))

Max Activating Token Index: 222

Text #18

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6141. Min Act: -0.0001

Data Index: 511964 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.8843. Min Range: -0.8843

Max Act: 0.6074. Min Act: -0.0001

Data Index: 1036516 (C4 (Web Text))

Max Activating Token Index: 877