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

Dataset: The Pile

Neuron 799 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1785742 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.2515. Min Range: -1.2515

Max Act: 1.2515. Min Act: -0.0000

Data Index: 866419 (The Pile)

Max Activating Token Index: 989

Text #2

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7691. Min Act: -0.0000

Data Index: 116142 (The Pile)

Max Activating Token Index: 731

Text #3

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1643218 (The Pile)

Max Activating Token Index: 859

Text #4

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1451181 (The Pile)

Max Activating Token Index: 700

Text #5

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.5699. Min Act: -0.0000

Data Index: 667336 (The Pile)

Max Activating Token Index: 801

Text #6

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.4825. Min Act: -0.0000

Data Index: 1922166 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.5355. Min Act: -0.0000

Data Index: 555934 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.6294. Min Act: -0.0000

Data Index: 694319 (The Pile)

Max Activating Token Index: 835

Text #9

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.5071. Min Act: -0.0000

Data Index: 1422536 (The Pile)

Max Activating Token Index: 236

Text #10

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.4678. Min Act: -0.0000

Data Index: 1115630 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.4712. Min Act: -0.0000

Data Index: 1717532 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.5303. Min Act: -0.0000

Data Index: 1940432 (The Pile)

Max Activating Token Index: 663

Text #13

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1986442 (The Pile)

Max Activating Token Index: 958

Text #14

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.4308. Min Act: -0.0000

Data Index: 606128 (The Pile)

Max Activating Token Index: 441

Text #15

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.2994. Min Act: -0.0000

Data Index: 1823508 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.4695. Min Act: -0.0000

Data Index: 882624 (The Pile)

Max Activating Token Index: 321

Text #17

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.5872. Min Act: -0.0000

Data Index: 600356 (The Pile)

Max Activating Token Index: 898

Text #18

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.4207. Min Act: -0.0000

Data Index: 394037 (The Pile)

Max Activating Token Index: 699

Text #19

Max Range: 1.2515. Min Range: -1.2515

Max Act: 0.3966. Min Act: -0.0000

Data Index: 1728537 (The Pile)

Max Activating Token Index: 1020