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

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

Neuron 4056 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7535. Min Range: -5.7535

Max Act: 5.7535. Min Act: -0.0001

Data Index: 366888 (C4 (Web Text))

Max Activating Token Index: 292

Text #1

Max Range: 5.7535. Min Range: -5.7535

Max Act: 5.4454. Min Act: -0.0001

Data Index: 1070094 (C4 (Web Text))

Max Activating Token Index: 468

Text #2

Max Range: 5.7535. Min Range: -5.7535

Max Act: 5.0119. Min Act: -0.0001

Data Index: 986665 (C4 (Web Text))

Max Activating Token Index: 783

Text #3

Max Range: 5.7535. Min Range: -5.7535

Max Act: 5.0510. Min Act: -0.0001

Data Index: 804626 (C4 (Web Text))

Max Activating Token Index: 549

Text #4

Max Range: 5.7535. Min Range: -5.7535

Max Act: 5.1648. Min Act: -0.0001

Data Index: 844348 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 5.7535. Min Range: -5.7535

Max Act: 5.2044. Min Act: -0.0001

Data Index: 958479 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7475. Min Act: -0.0001

Data Index: 666964 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.5681. Min Act: -0.0001

Data Index: 1216901 (C4 (Web Text))

Max Activating Token Index: 303

Text #8

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.8889. Min Act: -0.0001

Data Index: 638912 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7056. Min Act: -0.0001

Data Index: 85802 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.6793. Min Act: -0.0001

Data Index: 160232 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.8273. Min Act: -0.0001

Data Index: 400513 (C4 (Web Text))

Max Activating Token Index: 587

Text #12

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.8068. Min Act: -0.0001

Data Index: 1189690 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.3384. Min Act: -0.0001

Data Index: 1335550 (C4 (Web Text))

Max Activating Token Index: 676

Text #14

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7876. Min Act: -0.0001

Data Index: 336333 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7678. Min Act: -0.0001

Data Index: 991063 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7608. Min Act: -0.0001

Data Index: 975478 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7504. Min Act: -0.0001

Data Index: 177490 (C4 (Web Text))

Max Activating Token Index: 445

Text #18

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7309. Min Act: -0.0001

Data Index: 1140833 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 5.7535. Min Range: -5.7535

Max Act: 4.7139. Min Act: -0.0001

Data Index: 27532 (C4 (Web Text))

Max Activating Token Index: 169