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

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

Neuron 2275 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: 0.7667. Min Range: -0.7667

Max Act: 0.7667. Min Act: -0.0000

Data Index: 1255781 (C4 (Web Text))

Max Activating Token Index: 73

Text #1

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6870. Min Act: -0.0000

Data Index: 876334 (C4 (Web Text))

Max Activating Token Index: 198

Text #2

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7073. Min Act: -0.0000

Data Index: 844417 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7358. Min Act: -0.0000

Data Index: 484784 (C4 (Web Text))

Max Activating Token Index: 492

Text #4

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7306. Min Act: -0.0000

Data Index: 576449 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7169. Min Act: -0.0000

Data Index: 745569 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6667. Min Act: -0.0000

Data Index: 809749 (C4 (Web Text))

Max Activating Token Index: 608

Text #7

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6649. Min Act: -0.0000

Data Index: 30276 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6762. Min Act: -0.0000

Data Index: 939253 (C4 (Web Text))

Max Activating Token Index: 8

Text #9

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.7161. Min Act: -0.0000

Data Index: 629838 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1280836 (C4 (Web Text))

Max Activating Token Index: 645

Text #11

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6170. Min Act: -0.0000

Data Index: 632965 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6035. Min Act: -0.0000

Data Index: 570544 (C4 (Web Text))

Max Activating Token Index: 707

Text #13

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6187. Min Act: -0.0000

Data Index: 685858 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6278. Min Act: -0.0000

Data Index: 977031 (C4 (Web Text))

Max Activating Token Index: 648

Text #15

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6389. Min Act: -0.0000

Data Index: 980851 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.5723. Min Act: -0.0000

Data Index: 820579 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6498. Min Act: -0.0000

Data Index: 79620 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6022. Min Act: -0.0000

Data Index: 58284 (C4 (Web Text))

Max Activating Token Index: 465

Text #19

Max Range: 0.7667. Min Range: -0.7667

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1040211 (C4 (Web Text))

Max Activating Token Index: 194