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

Dataset: The Pile

Neuron 411 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1582012 (The Pile)

Max Activating Token Index: 993

Text #1

Max Range: 1.2431. Min Range: -1.2431

Max Act: 1.2407. Min Act: -0.0000

Data Index: 769338 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9013. Min Act: -0.0000

Data Index: 670285 (The Pile)

Max Activating Token Index: 956

Text #3

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9981. Min Act: -0.0000

Data Index: 1384140 (The Pile)

Max Activating Token Index: 822

Text #4

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9249. Min Act: -0.0000

Data Index: 403251 (The Pile)

Max Activating Token Index: 798

Text #5

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9856. Min Act: -0.0000

Data Index: 1796713 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8228. Min Act: -0.0000

Data Index: 793307 (The Pile)

Max Activating Token Index: 270

Text #7

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8299. Min Act: -0.0000

Data Index: 320045 (The Pile)

Max Activating Token Index: 965

Text #8

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.9281. Min Act: -0.0000

Data Index: 1799721 (The Pile)

Max Activating Token Index: 570

Text #9

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8008. Min Act: -0.0000

Data Index: 2613 (The Pile)

Max Activating Token Index: 605

Text #10

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.8596. Min Act: -0.0000

Data Index: 200341 (The Pile)

Max Activating Token Index: 846

Text #11

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1568548 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7085. Min Act: -0.0000

Data Index: 322481 (The Pile)

Max Activating Token Index: 982

Text #13

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7171. Min Act: -0.0000

Data Index: 1077043 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7573. Min Act: -0.0000

Data Index: 606935 (The Pile)

Max Activating Token Index: 950

Text #15

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7642. Min Act: -0.0000

Data Index: 1347507 (The Pile)

Max Activating Token Index: 714

Text #16

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1042268 (The Pile)

Max Activating Token Index: 569

Text #17

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7771. Min Act: -0.0000

Data Index: 620078 (The Pile)

Max Activating Token Index: 482

Text #18

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1623644 (The Pile)

Max Activating Token Index: 250

Text #19

Max Range: 1.2431. Min Range: -1.2431

Max Act: 0.7497. Min Act: -0.0000

Data Index: 1737221 (The Pile)

Max Activating Token Index: 989