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

Dataset: The Pile

Neuron 4723 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: 3.6330. Min Range: -3.6330

Max Act: 3.6330. Min Act: -0.0000

Data Index: 1325512 (The Pile)

Max Activating Token Index: 328

Text #1

Max Range: 3.6330. Min Range: -3.6330

Max Act: 3.1212. Min Act: -0.0000

Data Index: 392938 (The Pile)

Max Activating Token Index: 97

Text #2

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.5267. Min Act: -0.0000

Data Index: 1720746 (The Pile)

Max Activating Token Index: 196

Text #3

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.5342. Min Act: -0.0000

Data Index: 1085665 (The Pile)

Max Activating Token Index: 835

Text #4

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.3406. Min Act: -0.0000

Data Index: 1349988 (The Pile)

Max Activating Token Index: 756

Text #5

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.1450. Min Act: -0.0000

Data Index: 112338 (The Pile)

Max Activating Token Index: 604

Text #6

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.4929. Min Act: -0.0000

Data Index: 1403697 (The Pile)

Max Activating Token Index: 63

Text #7

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.4937. Min Act: -0.0000

Data Index: 436015 (The Pile)

Max Activating Token Index: 483

Text #8

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.1126. Min Act: -0.0000

Data Index: 1381326 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.1633. Min Act: -0.0000

Data Index: 854496 (The Pile)

Max Activating Token Index: 784

Text #10

Max Range: 3.6330. Min Range: -3.6330

Max Act: 2.1665. Min Act: -0.0000

Data Index: 61924 (The Pile)

Max Activating Token Index: 913

Text #11

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.9729. Min Act: -0.0000

Data Index: 1472667 (The Pile)

Max Activating Token Index: 454

Text #12

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.9299. Min Act: -0.0000

Data Index: 560513 (The Pile)

Max Activating Token Index: 137

Text #13

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.7867. Min Act: -0.0000

Data Index: 1703348 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.8719. Min Act: -0.0000

Data Index: 1241057 (The Pile)

Max Activating Token Index: 534

Text #15

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.7779. Min Act: -0.0000

Data Index: 768692 (The Pile)

Max Activating Token Index: 608

Text #16

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.7582. Min Act: -0.0000

Data Index: 1898798 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.8637. Min Act: -0.0000

Data Index: 348875 (The Pile)

Max Activating Token Index: 155

Text #18

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.9662. Min Act: -0.0000

Data Index: 1147767 (The Pile)

Max Activating Token Index: 193

Text #19

Max Range: 3.6330. Min Range: -3.6330

Max Act: 1.8626. Min Act: -0.0000

Data Index: 825594 (The Pile)

Max Activating Token Index: 310